Model Activations

Ask about this topic

Momentum

13 papers in the last four weeks, up 30% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 171

All topics
CardsList

  1. MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge

    Oct 6, 2026Mehmet Emre Akbulut, Johannes Geier, Ulf SchlichtmannModel Activations

    Technical University of Munich Munich, Germany

  2. Latent space bias directions in LLMs capture confidence, not fairness

    Oct 6, 2026Stephanie Buttigieg, Maeve Madigan, Parameswaran Kamalaruban +1Linear Activation SteeringLarge Language Model Bias

    Institute of Astronomy & Kavli Institute for Cosmology, University of Cambridge, UK · Risk and Security AI Lab, Visa Inc., Cambridge, UK

  3. Steering by Influence: Curvature Aware Data Weighting for Activation Steering

    Oct 5, 2026James A. E. Dixon, Stephen J. Roberts, Francesco QuinzanLinear Activation SteeringModel Activations

    Machine Learning Research Group, Department of Engineering Science University of Oxford

  4. Latent Information Sharing for Accelerating Federated Learning

    Oct 1, 2026Seungjun Lee, Ensieh Khazaei, Dimitrios Hatzinakos +2Federated LearningModel Activations

    Inha University · University of Toronto · University of Birmingham

  5. Kernelized Activation Steering

    Oct 1, 2026Laziz U. Abdullaev, Minh-Hieu Pham, Bach Do +2Linear Activation SteeringModel Activations

    Hanoi University of Science and Technology

  6. Alignment via Training Against Probes Without Losing Monitorability

    Sep 29, 2026Lena Libon, Alexander Panfilov, Ben Rank +3Safety AlignmentModel Activations

    ETH Zurich · ELLIS Institute Tübingen, MPI for Intelligent Systems, Tübingen AI Center

  7. Selecting The Most Informative Tokens in Natural Language Autoencoders

    Sep 29, 2026Federico Torrielli, Gianluca Barmina, Andrea Blasi Núñez +4Explainable AI MethodsModel Activations

    Department of Computer Science, University of Turin, Italy · Department of Mathematics and Computer Science, University of Southern Denmark, Denmark

  8. LLMs Learn to Evade Latent Monitors from Prior Feedback Alone

    Sep 29, 2026Hugo Lyons Keenan, Christopher Leckie, Sarah ErfaniModel ActivationsEvasion

    School of Computing and Information Systems The University of Melbourne, Victoria, Australia

  9. Persona Dosing: Calibrated Activation Steering for Graded Trait Control

    Sep 28, 2026Zehao Jin, Junran Wang, Ruixuan Deng +4PersonalityLinear Activation Steering

    Georgia Institute of Technology · Zhejiang University · University of British Columbia

  10. Signatures of semantic search in the activations of large language models

    Sep 28, 2026Luke Leckie, Peter M. Todd, Jacob G. FosterModel ActivationsFluency

    Department of Informatics, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN · Cognitive Science Program, Indiana University, Bloomington, IN · Center for Possible Minds, Indiana University, Bloomington, IN +2

  11. From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features

    Sep 28, 2026Dewen Liu, Zixuan Li, Jonathan Pan +4Mechanistic InterpretabilityModel Activations

    Tsinghua University · Fudan University · University of Edinburgh

  12. Understanding Confabulation and Rethinking Reconstruction in Activation Explanations

    Sep 27, 2026Gert Lek, Zixuan Xia, Pin-Yu Chen +1Model ActivationsExplainable AI Methods

    Universit´e de Neuchˆatel · Universität Bern · IBM Research +1

  13. Matryoshka attribution: Learning to attribute language model outputs to representations and weights

    Sep 22, 2026Aryaman Arora, Kirill Acharya, Nathan Hu +4Mechanistic InterpretabilityModel Activations

    Stanford University

  14. Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition

    Sep 16, 2026Devesh Tiwari, Camille Davis, Shivank Sinha +3Model ActivationsCausal Reasoning

    WW-P High School South · Phillips Academy Andover · Dublin High School +3

  15. What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track

    Sep 14, 2026Lingheng Du, Yiming Tang, Xufeng Duan +1Large Language Model Reinforcement LearningImproving Sparse Autoencoders

    Peking University · National University of Singapore · The Chinese University of Hong Kong

  16. GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models

    Sep 11, 2026Xuan Cuong Ngo, Hao Vo, Ngan LeLinear Activation SteeringModel Activations

    University of Arkansas, Fayetteville, Arkansas, USA

  17. SMILE: Bridging Continuous Optimization and Discrete Symbolic Recovery

    Sep 4, 2026Mansooreh Montazerin, Antonio Ortega, Ajitesh SrivastavaSymbolic RegressionModel Discovery

    Department of Electrical and Computer Engineering University of Southern California

  18. GAPS: Dimension-Level Gates for Conditional Activation Steering

    Sep 1, 2026Moghis Fereidouni, Muhammad Umair Haider, Hassan Sajjad +1Linear Activation SteeringModel Activations

    University of Kentucky · Dalhousie University

  19. Interpretable Symptom Vectors for Depression in a Large Language Model

    Sep 1, 2026Fangyi Zhu, Ajay Subramanian, Allison Constant +3DepressionModel Activations

    Department of Psychiatry & Behavioral Sciences, Stanford University School of Medicine, Stanford, CA, USA · Wu Tsai Neurosciences Institute, Stanford University, Stanford, CA, USA · Kaiser Permanente, San Jose, CA, USA +2

  20. Investigating Assistant Bias in LLM User Simulators Using a Role Vector

    Sep 1, 2026Daeheon Jeong, Yoonjoo Lee, Eugene Choi +2User SimulationBiases

    1KAIST · University of Michigan · 3Seoul National University +2

  21. Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models

    Aug 31, 2026Ashwin Nedungadi, Stefan Oehmcke, Stefan LüdtkeImage-To-Code GenerationSpatial Reasoning

    Institute for Visual & Analytic Computing (VAC), University of Rostock

  22. Probing and steering biology across Boltz-1s trunk-diffusion boundary

    Aug 11, 2026Piotr Jedryszek, Tongmeng Xie, Adam Winnifrith +5Protein Structure PredictionModel Activations

    Department of Biology, University of Oxford, Oxford, UK · Evolvere Biosciences, London, UK · Independent Researcher +4

  23. Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders

    Aug 11, 2026Nikolai Bolik, Lennart Stöpler, Artur AndrzejakSemantic RepresentationsModel Activations

    Heidelberg University

  24. Interpreting Language Model Hidden States at Scale

    Aug 10, 2026Jordan Pettyjohn, Mansi Sakarvadia, Nathaniel Hudson +3Model ActivationsHidden States

    University of Chicago · 2Illinois Institute of Technology · 3Argonne National Laboratory +1

  25. A Convolutional Layer Activation Dimensionality Reduction for Out-of-Distribution and Adversarial Attack Detection Methods

    Aug 10, 2026Leandro de Souza Rosa, Lorenzo Capelli, Clara Nunes Barrancos +2Final Convolutional LayersOut-Of-Distribution Detection

    Dipartimento di Ingegneria dell’Energia Elettrica e dell’Informazione “Guglielmo Marconi” (DEI) - Alma Mater Studiorum Università di Bologna, Bologna, Italy · Advanced Research Center on Electronic Systems “Ercole De Castro” (ARCES) - Alma Mater Studiorum Università di Bologna, Bologna, Italy

  26. One Adapter Pair per Model: A Universal Activation Interface for Language Models

    Aug 10, 2026Su-Hyeon Kim, Jiwan Mun, Yo-Sub HanModel Activations

    Department of Artificial Intelligence, Yonsei University · Department of Computer Science, Yonsei University

  27. Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models

    Aug 9, 2026Muhammad Faishal Adly Nelwan, Alfan Farizki WicaksonoLinear Activation SteeringModel Activations

    Faculty of Computer Science Universitas Indonesia

  28. Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families

    Aug 8, 2026Alizishaan Khatri, Dun Li ChanLarge Language Model SafetyModel Activations

    Wrynx Inc · INTI International College Penang

  29. Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes

    Aug 7, 2026Luc Hazenoot, Zhaochun Ren, Amirhossein ZohrehvandModel ActivationsText Analysis and Detection

    Leiden Institute of Advanced Computer Science, Leiden University

  30. Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors

    Aug 6, 2026Arya Labroo, Mengjie Qian, Kate KnillSpeakerLarge Language Model Bias

    University of Cambridge

  31. Looking in the Mirror: Introspecting Side-Effect Misalignments Induced by Fine-Tuning

    Aug 5, 2026Kotaro Yoshida, Laura Gomezjurado Gonzalez, Yukinori Yamamoto +3Introspection AdaptersModel Fine-Tuning

    Institute of Science Tokyo · 2ZOZO Research · 3Stanford University +2

  32. Calliphony: A Calligraphy-Driven Interface for Real-Time Generative Music Performance

    Aug 4, 2026Tristan Wu, Ruiji Yu, Gus XiaGenerative MusicHandwriting

    Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates

  33. Rewriting or Reweighting? A Geometric Account in Language Models

    Aug 3, 2026Juntong Wang, Shengkun Yang, Xiyuan Wang +1Behavioral Foundation ModelsModel Activations

    Institute for Artificial Intelligence, Peking University, Beijing, China · School of Intelligence Science and Technology, Peking University, Beijing, China · School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China

  34. Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations

    Jul 30, 2026Pere Martra, Eugenio Martínez Cámara, Alfonso Ureña LópezLarge Language Model BiasModel Activations

    Universidad Internacional Men´endez Pelayo Barcelona, Spain · Departamento de Inform´atica Universidad de Ja´en Ja´en, Spain

  35. Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs

    Jul 30, 2026Jinyi Liu, Wei Chen, Pengyu Chen +4LLM Inference OptimizationModel Activations

    Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences · School of Computer Science, Nanjing University of Posts and Telecommunications

  36. Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models

    Jul 28, 2026Deepanshu Mody, Samarth Agarwal, Utkarsh Mittal +1Model ActivationsLarge Language Model Safety

    Center for Data Science, New York University

  37. Forecasting Side Effects of Activation Steering

    Jul 28, 2026Chong Yong Ong, Alson Wei Jie Sim, Peixin Zhang +1Linear Activation SteeringSteering

    Singapore Management University

  38. Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects

    Jul 27, 2026Phu Gia Hoang, Anwoy Chatterjee, Tanmoy Chakraborty +2Sparse Autoencoder FeaturesInterpretability

    UKP Lab, Technical University of Darmstadt · Department of Electrical Engineering Indian Institute of Technology Delhi, India

  39. When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles

    Jul 25, 2026Tobias Bersia, Tatiana GaintsevaModel ActivationsRepresentation-Level Misalignment

    BAISH · Queen Mary University of London

  40. Token Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought Models

    Jul 23, 2026Renuka Oladri, Niveda Jawahar, Abdirisak MohamedChain-of-Thought ReasoningDeepseek

    Computer, Mathematical, and Natural Sciences University of Maryland College Park, MD, USA · University of Maryland SAP Labs, LLC College Park, MD, USA

  41. Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects

    Jul 22, 2026Seonglae Cho, Zekun Wu, Kleyton Da Costa +3Sparse Autoencoder FeaturesModel Activations

    Holistic AI · University College London

  42. Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations

    Jul 22, 2026Hiskias DingetoVerbalizationInterpretability

    StackOne Technologies

  43. Detecting Neural Network Failures through Spectral Analysis of Internal Activations

    Jul 22, 2026Arunan JSpectralModel Activations

    Independent Researcher

  44. OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization

    Jul 22, 2026Kavin Aravindan, Arihant Rastogi, Krishak Aneja +4Linear Activation SteeringModel Activations

    IIIT Hyderabad, India.

  45. Causal dictionary learning reveals and validates transcription-factor binding features in genomic language models

    Jul 21, 2026Sarwan AliUnsupervised Dictionary LearningExploratory Factor Analysis

    Columbia University Irving Medical Center, New York, USA

  46. Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence

    Jul 20, 2026Katarzyna Filus, Sebastian PokucińskiMechanistic InterpretabilitySemantic Representations

    Institute of Theoretical and Applied Informatics, Polish Academy of Sciences, Bałtycka 5, 44-100 Gliwice, Poland · Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland

  47. Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent

    Jul 17, 2026Sriram Balasubramanian, Soheil FeiziInterpretabilityModel Activations

    Department of Computer Science University of Maryland

  48. Transcoders for Investigating Deception in Language Models

    Jul 16, 2026Darius Lim, Nathan Leow, Xin Wei ChiaDeceptionMechanistic Interpretability

    Home Team Science & Technology Agency (HTX) Singapore

  49. Conditional Optimal Bridge for Riemannian Activation Steering

    Jul 12, 2026Seyed Arshan Dalili, Ajay Narayanan Sridhar, Vijaykrishnan Narayanan +1Linear Activation SteeringModel Activations

    The Pennsylvania State University

  50. Sensitivity-Aware Thresholding and Token Routing for Activation Sparsification in Large Language Models

    Jul 9, 2026Bishmoy Paul, Youngmin Yi, Hoeseok YangModel ActivationsToken-Level Uncertainty

    Santa Clara University · Sogang University

  51. Training, Reading, and Editing Legible Transformers

    Jul 9, 2026Mark OskinTransformer ArchitecturesModel Activations

    School of Computer Science and Engineering University of Washington

  52. Prompt Compression via Activation Aggregation

    Jul 9, 2026Thibaud Ardoin, Semira Einsele, Evis Bregu +1Large Language Model CompressionInstruction-Tuned Models

    Freie Universität Berlin

  53. A First-Principles Theory of Slow Thinking and Active Perception

    Jul 9, 2026Hongkang Yang, Zhi-Qin John Xu, Feiyu Xiong +1Cognitive ScienceModel Activations

    1MemTensor (Shanghai) Technology Co., Ltd. · Institute for Advanced Algorithms Research, Shanghai · 3Shanghai JiaoTong University +1

  54. Distributed Sparse Interventions in Language Models

    Jul 8, 2026Maximilian S. Ernst, Lorenz Linhardt, Aaron Peikert +1Latent Feature InterventionsNeurons

    Max Planck School of Cognition · Center for Lifespan Psychology Max Planck Institute for Human Development · Machine Learning Group Technische Universität Berlin +5

  55. Unsupervised Features Mining via Activation Geometry

    Jul 5, 2026Amit LeVi, Elad David, Max FominModel ActivationsLLM Reasoning Strategies

    Zenity Tel Aviv, Israel

  56. kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail

    Jul 2, 2026Mahmoud Abdelfattah, Hamid Nasiri, Peter GarraghanLarge Language Model SafetyAdversarial Prompts

    Lancaster University · Mindgard

  57. The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

    Jul 1, 2026Andrzej Szablewski, Gabriel Konar-Steenberg, Raffaello Fornasiere +2InterpretabilityMechanistic Interpretability

    1LASR Labs

  58. Mechanistically Eliciting Latent Behaviors in Language Models

    Jun 28, 2026Andrew Mack, Nina Panickssery, Alexander Matt TurnerModel ActivationsAgent Behavior Modeling

    †Principles of Intelligence · ‡Anthropic · §Independent

  59. Representational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Models

    Jun 28, 2026Archit ManekLarge Language Model EvaluationModel Activations

    Independent Researcher.

  60. Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies

    Jun 28, 2026Reza Habibi, Darian Lee, Magy Seif El-NasrMechanistic InterpretabilityBehavioral Foundation Models

    University of California, Santa Cruz