S 3martCirc: Self-supervised Smart Circuit Discovery

arXiv:2609.00755 · cs.AI · Submitted 2026-09-01 · Read on arXiv

cs.AI

Submitted: 2026-09-01

Updated: 2026-09-01

Terminology

• Interpretability — 20× in this paper · explained in 15 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• Mechanistic interpretability — 13× in this paper · explained in 2 episodes
• Sparsity — 9× in this paper · explained in 4 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Abstraction — 5× in this paper · explained in 1 episode
• Activation Patching — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Pruning — 3× in this paper · explained in 4 episodes
• Indirect Object Identification — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Discovery First — 1× in this paper
• Ensemble Learning — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Interpretation First — 1× in this paper
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• No Warmup — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes
• Uncertainty Quantification — 1× in this paper · explained in 8 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Text Summarization Using Large Language Models: A Comparative Study of MPT-7b-instruct, Falcon-7b-instruct, and OpenAI Chat-GPT Models
• Mechanistic Interpretability for AI Safety -- A Review
• IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck
• Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective
• TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement
• Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability
• The Llama 3 Herd of Models
• Pitfalls in Evaluating Interpretability Agents
• Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
• SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
• How to use and interpret activation patching
• Science Across Languages: Assessing LLM Multilingual Translation of Scientific Papers
• How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective
• Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?
• Progress measures for grokking via mechanistic interpretability
• A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
• Open Problems in Mechanistic Interpretability
• Rethinking Interpretability in the Era of Large Language Models
• Attribution Patching Outperforms Automated Circuit Discovery
• Beyond the Black Box: Interpretability of LLMs in Finance

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection