Local Ai
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
arXiv:2601.14004v4 Announce Type: replace Abstract: Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However,
arXiv:2601.14004v4 Announce Type: replace Abstract: Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical insights while lacking a systematic framework for actionable intervention. To bridge this gap, we present a practical survey structured around the pipeline: "Locate, Steer, and Improve." We formally categorize Localizing (diagnosis) and Steering (intervention) methods based on specific Interpretable Objects to establish a rigorous intervention protocol. Furthermore, we demonstrate how this framework enables tangible improvements in Alignment, Capability, and Efficiency, effectively operationalizing MI as an actionable methodology for model optimization. The curated paper list of this work is available at https://github.com/rattlesnakey/Awesome-Actionable-MI-Survey.
Related
- Different types of syntactic agreement recruit the same units within large language models
- Psychological Concept Neurons: Can Neural Control Bias Probing and Shift Generation in LLMs?
- Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution
- Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
- Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation
Source: arXiv cs.CL | 2026-04-15