Who cites «Finding Neurons in a Haystack: Case Studies with Sparse Probing»
- Do Llamas Work in English? On the Latent Language of Multilingual TransformersAnnual Meeting of the Association for Computational Linguistics (ACL)Chris Wendler, Veniamin Veselovsky, Giovanni Monea, et al.2024 · 177 citations
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False DatasetsarXiv:2310.06824Samuel Marks, Max Tegmark2023 · 169 citations
- Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Tianyi Tang, Wenyang Luo, Haoyang Huang, et al.2024 · 156 citations
- Emergent Linear Representations in World Models of Self-Supervised Sequence ModelsarXiv:2309.00941Neel Nanda, Andrew Lee, Martin Wattenberg2023 · 116 citations
- Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2arXiv:2408.05147Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, et al.2024 · 115 citations
- Mechanistic Interpretability for AI Safety — A ReviewarXiv:2404.14082Leonard Bereska, Efstratios Gavves2024 · 108 citations
- Towards Best Practices of Activation Patching in Language Models: Metrics and MethodsarXiv:2309.16042Fred Zhang, Neel Nanda2023 · 97 citations
- Do Llamas Work in English? On the Latent Language of Multilingual TransformersAnnual Meeting of the Association for Computational Linguistics (ACL)Chris Wendler, Veniamin Veselovsky, Giovanni Monea, et al.2024 · 96 citations
- Rethinking Interpretability in the Era of Large Language ModelsarXiv:2402.01761Chandan Singh, Jeevana Priya Inala, Michel Galley, et al.2024 · 87 citations
- A Primer on the Inner Workings of Transformer-based Language ModelsarXiv:2405.00208Javier Ferrando, Gabriele Sarti, Arianna Bisazza, et al.2024 · 72 citations
- Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse AutoencodersarXiv:2410.20526Zhengfu He, Wentao Shu, Xuyang Ge, et al.2024 · 63 citations
- Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in ChinchillaarXiv:2307.09458Tom Lieberum, Matthew Rahtz, Janos Kramar, et al.2023 · 58 citations
- Future Lens: Anticipating Subsequent Tokens from a Single Hidden StateConference on Computational Natural Language Learning (CoNLL)Koyena Pal, Jiuding Sun, Andrew Yuan, et al.2023 · 49 citations
- Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Mingyang Wang, Heike Adel, Lukas Lange, et al.2025 · 31 citations
- What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient PerspectiveAnnual Meeting of the Association for Computational Linguistics (ACL)Ming Li, Yanhong Li, Tianyi Zhou2025 · 15 citations
- Route Sparse Autoencoder to Interpret Large Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Wei Shi, Sihang Li, Tao Liang, et al.2025 · 11 citations
- Paths Not Taken: Understanding and Mending the Multilingual Factual Recall PipelineConference on Empirical Methods in Natural Language Processing (EMNLP)Meng Lu, Ruochen Zhang, Carsten Eickhoff, et al.2025 · 9 citations
- Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward PassesAnnual Meeting of the Association for Computational Linguistics (ACL)Bryan R Christ, Zachary Gottesman, Jonathan Kropko, et al.2025 · 7 citations
- Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation FrameworkFindings of the Association for Computational LinguisticsJiaqi Weng, Han Zheng, Hanyu Zhang, et al.2026 · 2 citations
- Towards Controllable Natural Language Inference through Lexical Inference TypesarXiv:2308.03581Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann, et al.2023 · 2 citations
- Constructing Interpretable Features from Compositional Neuron GroupsAnnual Meeting of the Association for Computational Linguistics (ACL)Or David Shafran, Atticus Geiger, Mor Geva2026 · 1 citation
- Tug-of-war between idioms' figurative and literal interpretations in LLMsConference of the European Chapter of the Association for Computational Linguistics (EACL)Soyoung Oh, Xinting Huang, Mathis Pink, et al.2026 · 1 citation
- Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Jiayi Zhang, Shu Yang, Junchao Wu, et al.2026 · 1 citation
- Vocab Diet: Reshaping the Vocabulary of LLMs via Vector ArithmeticFindings of the Association for Computational LinguisticsYuval Reif, Guy Kaplan, Roy Schwartz2026 · 1 citation
- AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model RepresentationsFindings of the Association for Computational LinguisticsYifei Yao, Hanrong Zhang, Mengnan Du2026
- Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language ModelsFindings of the Association for Computational LinguisticsHanqi Yan, Xiangxiang Cui, Lu Yin, et al.2026
- From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?Annual Meeting of the Association for Computational Linguistics (ACL)Aaron Mueller, Andrew Lee, Shruti Joshi, et al.2026
- Mechanistic Insights into Deferred Semantic Drift in LLMsFindings of the Association for Computational LinguisticsJingjie Zeng, Huayang Li, Liang Yang, et al.2026
- Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language ModelsFindings of the Association for Computational LinguisticsZhen Yang, Xinyue Zhang, Ping Jian, et al.2026
This page in Markdown → https://md.research.elamur.ai/free/en/papers/gurnee-2023-finding-neurons-haystack-case-studies/cited-by/