Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
This work addresses the problem of making mechanistic interpretability more practical and actionable for researchers and practitioners working with large language models, though it is incremental as it builds on existing observational approaches.
The authors tackled the lack of actionable frameworks in mechanistic interpretability for large language models by proposing a structured pipeline called 'Locate, Steer, and Improve' to enable systematic intervention and optimization, resulting in a practical survey that categorizes methods and demonstrates improvements in alignment, capability, and efficiency.
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.