LLM Interpretability

LLM: Large Language Model

Overview

Large language model interpretability asks what information models represent, how it moves through layers and components, and which computations cause particular answers or behaviors. Researchers use probes and representation geometry, sparse autoencoders, attribution and circuit tracing, activation patching or ablation, and steering to study factual recall, mathematical reasoning, hallucination, refusal, and in-context learning. These methods can reveal distributed circuits and layer-wise signals, and sometimes support targeted interventions without retraining. A central challenge is that information being decodable—or a direction being steerable—does not prove the model uses it; causal faithfulness, robustness across prompts and model families, and reliable evaluation remain open tensions.

Latest papers

CardsList

841 papers55 papers in the last four weeks, down 36% on the four weeks before. 0.4% of all new papers.

  1. Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models

    Jan 12, 2026Zhenghao He, Guangzhi Xiong, Bohan Liu +2LLM InterpretabilityCoT Reasoning

  2. Tracing Moral Foundations in Large Language Models

    Jan 9, 2026Chenxiao Yu, Bowen Yi, Farzan Karimi-Malekabadi +5Moral Reasoning in Language ModelsMoral Reasoning

  3. Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control

    Jan 6, 2026Harshvardhan Saini, Yiming Tang, Dianbo LiuLanguage Model SteeringLLM Interpretability

  4. AlignSAE: Concept-Aligned Sparse Autoencoders

    Dec 1, 2025Minglai Yang, Xinyu Guo, Zhengliang Shi +4Sparse AutoencodersLLM Interpretability

  5. Rep2Text: Decoding Full Text from a Single LLM Token Representation

    Nov 9, 2025Haiyan Zhao, Zirui He, Yiming Tang +4LLM InterpretabilityLLM Information Extraction

  6. TOPol: Reconstructing and Interpreting Multidimensional Semantic Polarity Fields

    Oct 29, 2025Lucia Gomez, Gabin Taibi, Julius Sipke KooistraLLM InterpretabilitySentiment Analysis

  7. Fine-grained Analysis of Brain-LLM Alignment through Input Attribution

    Oct 14, 2025Michela Proietti, Roberto Capobianco, Mariya TonevaLLM InterpretabilityNext-Token Prediction

  8. Base Models Know How to Reason, Thinking Models Learn When

    Oct 8, 2025Constantin Venhoff, Iván Arcuschin, Philip Torr +2LLM InterpretabilityRL for Language Model Reasoning

  9. Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning

    Sep 1, 2025Kaviraj Pather, Elena Hadjigeorgiou, Arben Krasniqi +4LLM InterpretabilityHuman-in-the-Loop AI

  10. A Financial Brain Scan of the LLM

    Aug 29, 2025Hui Chen, Antoine Didisheim, Mo Pourmohammadi +2LLM InterpretabilityLanguage Model Steering

  11. Unraveling the cognitive patterns of Large Language Models through module communities

    Aug 25, 2025Kushal Raj Bhandari, Pin-Yu Chen, Jianxi GaoComputational Cognitive ModelingLLM Interpretability

  12. Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders

    Aug 22, 2025David Chanin, Adrià Garriga-AlonsoActivation SparsityLLM Interpretability

  13. BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection

    Aug 12, 2025Sekh Mainul Islam, Nadav Borenstein, Siddhesh Milind Pawar +3Social Bias in Language ModelsLLM Interpretability

  14. Too Categorical to be Human: Emotion Concepts in LLMs and Humans

    Aug 7, 2025Sree Bhattacharyya, Evgenii Kuriabov, Lucas Craig +4LLM InterpretabilityEmotion Representation in Language Models

  15. LLMs Encode Harmfulness and Refusal Separately

    Jul 16, 2025Jiachen Zhao, Jing Huang, Zhengxuan Wu +2LLM InterpretabilityLLM Refusal Behavior

  16. Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages

    Jul 15, 2025Lyzander Marciano Andrylie, Inaya Rahmanisa, Mahardika Krisna Ihsani +3Multilingual Language ModelsRepresentation Learning

  17. On the Effect of Uncertainty on Layer-wise Inference Dynamics

    Jul 9, 2025Sunwoo Kim, Haneul Yoo, Alice OhLLM InferenceLLM Interpretability

  18. The Trilemma of Truth in Large Language Models

    Jun 30, 2025Germans Savcisens, Tina Eliassi-RadLLM InterpretabilityLLM Reliability

  19. InverseScope: Scalable Activation Inversion for Interpreting Large Language Models

    Jun 9, 2025Yifan Luo, Zhennan Zhou, Bin DongRepresentation GeometryLLM Interpretability

  20. Localizing Persona Representations in LLMs

    May 30, 2025Celia Cintas, Miriam Rateike, Erik Miehling +2LLM InterpretabilityPersonality Modeling in Language Models

  21. When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

    May 21, 2025Rongzhi Zhu, Yi Liu, Jiancheng Wang +6Overthinking in Language ModelsLLM Interpretability

  22. Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations

    Apr 7, 2025Pedro Ferreira, Wilker Aziz, Ivan TitovCoT FaithfulnessReward Hacking

  23. Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations

    Mar 17, 2025Noah Y. Siegel, Nicolas Heess, Maria Perez-Ortiz +1Faithfulness of Language Model ExplanationsLLM Interpretability

  24. LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

    Feb 20, 2025Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev +4Transformer InterpretabilityLong-Context Language Modeling

  25. Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning

    Dec 14, 2024Julia Witte Zimmerman, Denis Hudon, Kathryn Cramer +9LLM InterpretabilityDistributional Semantics