LLM Interpretability

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

57 papers in the last four weeks, up 73% on the four weeks before. 0.6% of all new papers.

Jul 13Week of Sep 28

Latest papers 546

All topics

Representation Without Control: Testing the Realization Effect in Language Models
May 24, 2026Ciarán Walsh, Emilio BarkettLLM Interpretability Causal Interventions in Language Models
Columbia University
Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts
May 24, 2026Xiangtian Ji, Yuxin Chen, Zhengzhou Cai +3Fine-Tuning LLM Interpretability
National University of Singapore · Beijing University of Posts and Telecommunications · University of Science and Technology of China
Building Better Activation Oracles
May 23, 2026Jan Bauer, Celeste De Schamphelaere, Adam Karvonen +2LLM Interpretability Mechanistic Interpretability
MATS · Gatsby Unit, UCL · Ghent University +2
Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
May 22, 2026Jinghan Jia, Joe Benton, Eric EasleyCoT Faithfulness LLM Interpretability
†Dept. CSE, Michigan State University · ⋆Anthropic Fellows Program · ‡Anthropic
Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning
May 22, 2026Muhammad Usama, Dong Eui ChangRepresentational Similarity Analysis LLM Interpretability
Control Laboratory, School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon 34141, Republic of Korea · Control Laboratory, School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST)2026 Daejeon 34141, Republic of Korea
As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs
May 22, 2026Eric XuLLM Prompting LLM Interpretability
Independent Researcher
The Attribution Contract: Feature Attribution for Generative Language Models
May 21, 2026Giang NguyenFeature Attribution LLM Interpretability
Guide Labs
Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
May 21, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuNeural Processes LLM Interpretability
The University of Hong Kong · Hong Kong, China · Stellaris AI Limited
Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
May 21, 2026Meimingwei Li, Yuanhao Ding, Esteban Garces Arias +1LLM Interpretability LLM Fine-Tuning
Department of Statistics, LMU Munich · School of Computer and Information Engineering, Henan University · Munich Center for Machine Learning (MCML)
Relational Linear Properties in Language Models: An Empirical Investigation
May 21, 2026Giovanni Valer, Luigi Gresele, Marco Bronzini +1LLM Interpretability Factual Knowledge in Language Models
Fondazione Bruno Kessler, Trento, Italy · University of Bologna, Bologna, Italy · University of Pisa, Pisa, Italy +2
Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
May 21, 2026Jewon Yeom, Jaewon Sok, Heejun Kim +3LLM Interpretability Hallucination in Language Models
Graduate School of Data Science, Seoul National University · Department of Rural Systems Engineering, Seoul National University · Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology +1
Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have)
May 21, 2026Hisashi MiyashitaLLM Auditing LLM Interpretability
Mgnite Inc.
Probabilistic Attribution For Large Language Models
May 20, 2026Shilpika Shilpika, Carlo Graziani, Bethany Lusch +2LLM Interpretability LLM Uncertainty Estimation
Argonne Leadership Computing Facility Argonne National Laboratory Lemont, IL, USA · Mathematics and Computer Science Division Argonne National Laboratory Lemont, IL, USA · Department of Computer Science University of Illinois Chicago Chicago, IL, USA
Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs
May 19, 2026Edie Pearman, Sophia Osborne, Mira Kandlikar-Bloch +3Gender Bias in Language Models LLM Interpretability
1Mila – Quebec AI Institute, Montreal, Canada · 2McGill University, Montreal, Canada · 3HEC Montreal, Montreal, Canada
Language models struggle with compartmentalization
May 19, 2026Thomas Vincent Howe, David WingateMultilingual Language Models LLM Interpretability
Department of Computer Science · Brigham Young University · Provo, UT 84602
Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations
May 19, 2026Somnath Banerjee, Pranav Jha, Rima Hazra +1Multilingual Language Model Evaluation Faithfulness of Language Model Explanations
Indian Institute of Technology Kharagpur · TCG Crest · National University of Singapore
Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels
May 18, 2026Alexander Boesgaard LorupCounterfactual Evaluation LLM Interpretability
Openhagen
Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics
May 18, 2026Maciej Chrabąszcz, Aleksander Szymczyk, Marcin Sendera +2Language Model Safety Evaluation LLM Interpretability
NASK - National Research Institute, Poland · Faculty of Electronics and Information Technology, Warsaw University of Technology, Poland · Faculty of Mathematics and Computer Science, Jagiellonian University, Poland +3
Probing for Representation Manifolds in Superposition
May 18, 2026Alexander ModellFeature Superposition Neural Representation Geometry
Department of Mathematics Imperial College London, U.K.
Are Sparse Autoencoder Benchmarks Reliable?
May 18, 2026David ChaninBenchmark Auditing LLM Interpretability
Decode Research, MATS, UCL
iPOE: Interpretable Prompt Optimization via Explanations
May 18, 2026Jiahui Li, Yarik Menchaca Resendiz, Sean Papay +1LLM Interpretability LLM-Assisted Annotation
Fundamentals of Natural Language Processing, University of Bamberg, Germany · Leibniz-Institut für Psychologie (ZPID), Trier, Germany
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
May 18, 2026Junyao Yang, Chen Qian, Kun Wang +4LLM Interpretability RL for Language Model Reasoning
National University of Singapore · Renmin University of China · Nanyang Technological University +1
The Point of No Return: Counterfactual Localization of Deceptive Commitment in Language-Model Reasoning
May 16, 2026Scott Merrill, Shashank SrivastavaLanguage Model Safety Evaluation LLM Interpretability
University of North Carolina at Chapel Hill
Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents
May 16, 2026Weicheng XueLLM Alignment LLM Auditing
Virginia Tech
Artificial Aphasias in Lesioned Language Models
May 15, 2026Nathan Roll, Jill Kries, Laura Gwilliams +1LLM Interpretability Causal Interventions in Language Models
Department of {1Linguistics, 2Psychology}, Stanford University · 3Wu Tsai Neurosciences Institute, Stanford University
Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge
May 15, 2026Nils Feldhus, Tanja Baeumel, Elena Golimblevskaia +10LLM-as-a-Judge LLM Interpretability
CLCG, University of Groningen · German Research Center for Artificial Intelligence (DFKI) · Centre for European Research in Trusted AI (CERTAIN) +5
Reasoning Models Don't Just Think Longer, They Move Differently
May 14, 2026Anders Gjølbye, Lars Kai Hansen, Sanmi KoyejoLLM Interpretability Representation Geometry in Language Models
Technical University of Denmark · Stanford University
Neural Activation Patterns Across Language Model Architectures: A Comprehensive Analysis of Cognitive Task Performance
May 14, 2026Mahdi Naser-Moghadasi, Faezeh GhaderiLLM Evaluation Decoder-Only Language Models
Research Division, BrightMind AI, Seattle, WA · Texas Tech University, Lubbock, TX · University of Texas at Arlington
Non-linear Interventions on Large Language Models
May 14, 2026Sangwoo KimLLM Interpretability Causal Interventions in Language Models
Department of Linguistics, Seoul National University, Republic of Korea.
Exploring Geographic Relative Space in Large Language Models through Activation Patching
May 14, 2026Stef De Sabbata, Rahul Baiju, Stefano Mizzaro +1LLM Interpretability
School of Geography, Geology and the Environment, University of Leicester, UK · Department of Mathematics, Computer Science and Physics, University of Udine, Italy

May 24, 2026, cs.AIJ/K move · Enter open · S save

Representation Without Control: Testing the Realization Effect in Language Models

Ciarán Walsh, Emilio Barkett

Columbia University

LLM Interpretability Causal Interventions in Language Models

Open paper AskPDF arXiv

Large language models are increasingly used as behavioral simulators, but it remains unclear when their outputs reflect human-like cognitive mechanisms rather than prompt-sensitive surface patterns. We study this question through the realization effect, a well-characterized finding in behavioral economics in which risk-taking differs systematically after paper versus realized gains and losses. We evaluate LLM behavior at three levels: prompt-only behavioral sensitivity, linear readout of internal representations, and causal control via activation steering. Prompt-only results show systematic condition sensitivity, but the directional pattern does not reproduce human realization-effect predictions. Gemma's residual stream contains a linearly decodable realization-status signal at layer 18 that generalizes to held-out prompts. Steering along this direction does not, however, reliably shift downstream risk choices, a null result that holds across positive scales and in a negative sign-symmetry run. Behavioral sensitivity, latent readout, and causal control are three distinct properties that do not automatically co-occur, and successful latent readout is insufficient evidence that a model behaviorally relies on a representation during downstream decision-making.

Momentum

Related topics

Latest papers 546