Circuits in Language Models

Follow this topic Ask about this topic

Circuits in language models are groups of attention heads, MLP neurons, and learned features whose interactions support behaviors such as induction, factual recall, arithmetic, refusal, and multilingual routing. Researchers locate them with activation patching and ablation, attribution graphs, and sparse autoencoders or transcoders, then test their causal roles on controlled tasks such as indirect object identification and greater-than. Some computations appear compact and reusable, while others are distributed, context-dependent, or reorganized by architecture and post-training. A central challenge is showing that a discovered circuit is causally faithful and task-specific rather than an artifact of prompts, analysis choices, or intervention side effects.

Latest papers

122 papers27 papers in the last four weeks, up 42% on the four weeks before. 0.2% of all new papers.

Data-driven Circuit Discovery for Interpretability of Language Models
May 9, 2026Daking Rai, Mor Geva, Ziyu YaoCircuit Discovery LLM Interpretability
George Mason University · Tel Aviv University
Architecture, Not Scale: Circuit Localization in Large Language Models
May 9, 2026Sohan VenkateshTransformer Interpretability Grouped-Query Attention
Manipal Institute of Technology Bengaluru.
How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits
May 8, 2026Michael Li, Nishant SubramaniCircuit Discovery Mechanistic Interpretability
Northeastern University · Carnegie Mellon University – Language Technologies Institute
Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training
May 7, 2026Hang Chen, Jiaying Zhu, Hongyang Chen +3Supervised Fine-Tuning Transformer Interpretability
School of Computer Science and Technology Xi’an Jiaotong University · School of Computer Science and Engineering The Chinese University of Hong Kong · Shaanxi Co., Ltd(Xi’an 710077, China) China Mobile Group +1
CircuitFormer: A Circuit Language Model for Analog Topology Design from Natural Language Prompt
May 7, 2026Md Touhidul Islam, Sujan Kumar Saha, Farimah Farahmandi +1Electronic Design Automation Language Modeling
University of Florida
Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs
Apr 30, 2026Hongliang Liu, Tung-Ling Li, Yuhao WuLLM Interpretability Mechanistic Interpretability
Palo Alto Networks
Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer
Apr 27, 2026Shun Shao, Binxu Wang, Shay B. Cohen +2LLM Interpretability Mechanistic Interpretability
University of Cambridge · Kempner Institute, Harvard University · University of Edinburgh +1
LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit
Apr 21, 2026Manav PandeyLLM Sycophancy LLM Alignment
Georgia Institute of Technology
A Mechanistic Account of Attention Sinks in GPT-2: One Circuit, Broader Implications for Mitigation
Apr 16, 2026Yuval Ran-Milo, Hila Ofek, Shahar MendelSelf-Attention Decoder-Only Language Models
Tel Aviv University
Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion
Apr 11, 2026Vishal Pramanik, Maisha Maliha, Susmit Jha +1Adversarial Attacks on LLMs LLM Jailbreak Attacks
Department of Computer & Information Science & Engineering, University of Florida, Gainesville, FL 32611, USA · School of Computer Science, University of Oklahoma, Norman, OK 73019, USA · Computer Science Laboratory, SRI International, Menlo Park, CA 94025, USA
What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
Apr 9, 2026Stephen Cheng, Sarah Wiegreffe, Dinesh ManochaLanguage Model Steering LLM Interpretability
University of Maryland, College Park
ADAG: Automatically Describing Attribution Graphs
Apr 8, 2026Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt +1Mechanistic Interpretability Circuits in Language Models
Stanford University · Transluce
Addressing the Reasoning Gap: Mechanistic Circuit-Based Knowledge Editing in Large Language Models
Apr 7, 2026Tianyi Zhao, Yinhan He, Wendy Zheng +1Knowledge Editing Factual Knowledge in Language Models
University of Virginia
Darkness Visible: Reading the Exception Handler of a Language Model
Apr 6, 2026Peter BaloghConcept Localization in Language Models LLM Interpretability
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
Apr 6, 2026Gregory N. FrankLLM Interpretability LLM Safety
Chief Scientist, Molt AI Corp.
CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders
Apr 2, 2026Su-Hyeon Kim, Hyundong Jin, Yejin Lee +1Refusal Behavior in Language Models Mechanistic Interpretability
Yonsei University, Seoul, Republic of Korea
Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models
Apr 1, 2026Itay Yona, Dan Barzilay, Michael Karasik +1Concept Localization in Language Models LLM Interpretability
Mentaleap · Independent Researcher · Tel Aviv University
From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks
Apr 1, 2026Ayan Datta, Mounika Marreddy, Alexander Mehler +2Symbolic Reasoning in Language Models LLM Interpretability
IIIT Hyderabad · Goethe University, Frankfurt am Main, Germany · University of Sheffield, UK
CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
Apr 1, 2026Rajkiran PanugantiCircuits in Language Models Transformer Interpretability
Independent Researcher
Entanglement as Memory: Mechanistic Interpretability of Quantum Language Models
Mar 27, 2026Nathan RollLong-Range Dependency Modeling Circuits in Language Models
Department of Linguistics, Stanford University
SafeSeek: Universal Attribution of Safety Circuits in Language Models
Mar 24, 2026Miao Yu, Siyuan Fu, Moayad Aloqaily +6LLM Interpretability Circuits in Language Models
University of Science and Technology of China · Squirrel Ai Learning · United Arab Emirates University +3
Discovering Decoupled Functional Modules in Large Language Models
Mar 18, 2026Yanke Yu, Jin Li, Ying Sun +3LLM Interpretability Circuits in Language Models
Thrust of AI, Hong Kong University of Science and Technology (Guangzhou) · Huawei Technologies Ltd.
Interpreting Negation in GPT-2: Layer- and Head-Level Causal Analysis
Mar 12, 2026Abdullah Al Mofael, Lisa M. Kuhn, Ghassan Alkadi +1Language Modeling Circuits in Language Models
∗Department of Computer Science, Southeastern Louisiana University, Hammond, LA, USA · †Department of Mathematics, Southeastern Louisiana University, Hammond, LA, USA
The Discrete Charm of the MLP: Binary Routing of Continuous Signals in Transformer Feed-Forward Layers
Mar 11, 2026Peter BaloghTransformer FFNs Transformer Interpretability
Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping
Mar 6, 2026Zhenyu Lei, Qiong Wu, Jianxiong Dong +4Language Model Editing LLM Reasoning
University of Virginia · AT&T Chief Data Office · Florida State University
CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles
Feb 28, 2026Swapnil ParekhCircuit Discovery Circuits in Language Models
Intuit
France or Spain or Germany or France: A Neural Account of Non-Redundant Redundant Disjunctions
Feb 26, 2026Sasha Boguraev, Qing Yao, Kyle MahowaldPragmatic Reasoning in Language Models Circuits in Language Models
Department of Linguistics, The University of Texas at Austin
Certified Circuits: Stability Guarantees for Mechanistic Circuits
Feb 26, 2026Alaa Anani, Tobias Lorenz, Bernt Schiele +2Circuit Discovery Mechanistic Interpretability
Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany · CISPA Helmholtz Center for Information Security, Saarbrücken, Germany
IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck
Feb 26, 2026Tian Bian, Yifan Niu, Chaohao Yuan +7Circuit Discovery Circuits in Language Models
Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China · DAMO Academy, Alibaba Group, Hangzhou, China · Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China +4
Post-Routing Arithmetic in Llama-3: Last-Token Result Writing and Rotation-Structured Digit Directions
Feb 22, 2026Yao YanNumerical Reasoning in Language Models Circuits in Language Models
Chongqing Normal University Chongqing Key Lab of Cognitive Intelligence and Intelligent Finance Chongqing, China

May 9, 2026J/K move · Enter open · S save

Data-driven Circuit Discovery for Interpretability of Language Models

Daking Rai, Mor Geva, Ziyu Yao

George Mason University · Tel Aviv University

Circuit Discovery LLM Interpretability Circuits in Language Models

Open paper AskPDF arXiv

Circuit study aims to explain how language models (LMs) implement a task by localizing and interpreting a circuit: a computational subgraph responsible for a specific model's behavior. Existing methods for circuit localization are largely hypothesis-driven: they define a task through a dataset, assume that all examples in the task are implemented by the same mechanism, and apply circuit discovery to obtain a single circuit. This workflow does not account for mechanistic diversity within a task, where different examples may rely on different mechanisms. We first show that when a dataset mixes tasks processed through distinct mechanisms, current circuit discovery can combine these mechanisms into a single circuit while retaining faithfulness comparable to circuits discovered on each task separately. Across four tasks and three models, we further provide evidence for such mechanistic diversity within individual tasks. To account for this diversity, we propose Data-driven Circuit Discovery (DCD), which modifies the circuit-discovery workflow by adding a grouping step before the discovery. The grouping step aims to partition the dataset into subsets of examples that rely on similar mechanisms. We instantiate this step with clustering over per-example attribution patterns (DCD-Cluster). Across four tasks and three models, DCD-Cluster decomposes the dataset into multiple subsets whose circuits exhibit distinct faithfulness patterns, providing useful hypotheses about mechanistic differences among examples.