# Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning

arXiv: https://arxiv.org/abs/2608.24482 · HTML: https://mlsanity.com/paper/2608.24482/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Circuits and mechanistic analysis, one of 13 directions in Mechanistic interpretability.
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Placed in

- Mechanistic interpretability / [Circuits and mechanistic analysis](https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/)

## Builds on (most cited first, 26 of 26)

- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [How to use and interpret activation patching](https://mlsanity.com/paper/2404.15255/) (2024)
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023)
- [Open Problems in Mechanistic Interpretability](https://mlsanity.com/paper/2501.16496/) (2025)
- [A Comprehensive Study of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2401.01286/) (2024)
- [Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla](https://mlsanity.com/paper/2307.09458/) (2023)
- [Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking](https://mlsanity.com/paper/2402.14811/) (2024)
- [A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models](https://mlsanity.com/paper/2407.02646/) (2024)
- [Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks](https://mlsanity.com/paper/2311.12786/) (2023)
- [Task-Specific Skill Localization in Fine-tuned Language Models](https://mlsanity.com/paper/2302.06600/) (2023)
- [Finding Transformer Circuits with Edge Pruning](https://mlsanity.com/paper/2406.16778/) (2024)
- [LoFiT: Localized Fine-tuning on LLM Representations](https://mlsanity.com/paper/2406.01563/) (2024)
- [Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization](https://mlsanity.com/paper/2410.12949/) (2024)
- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models](https://mlsanity.com/paper/2410.17509/) (2024)
- [Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis](https://mlsanity.com/paper/2502.11812/) (2025)
- [Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates](https://mlsanity.com/paper/2505.10039/) (2025)
- [CLUE: Conflict-guided Localization for LLM Unlearning Framework](https://mlsanity.com/paper/2509.20977/) (2025)
- [Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training](https://mlsanity.com/paper/2605.06076/) (2026)
- [Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification](https://mlsanity.com/paper/2503.01896/) (2025)
- [A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL](https://mlsanity.com/paper/2606.02398/) (2026)
- [Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders](https://mlsanity.com/paper/2605.27354/) (2026)
- [Skill Path: Unveiling Language Skills from Circuit Graphs](https://mlsanity.com/paper/2410.01334/) (2024)

## Abstract (arXiv)

Mechanistic Localization bridges mechanistic interpretability and post-training optimization by isolating critical parameters via interpretative approaches and then guiding parameter-efficient Supervised Fine-Tuning (SFT) in a ``locating-then-tuning'' paradigm. However, due to the retrospective nature of mechanistic interpretability, directly interpreting pre-SFT models introduces misleading conclusions. Specifically for novel tasks, initially identified neurons differ drastically from those governing the final model, introducing biases that actively disrupt SFT. To address this, we propose a forward-looking localization framework that accurately estimates the post-SFT interpretability state using only pre-SFT parameters and the target dataset. Theoretically, we model SFT as a continuous parameter evolution, leveraging Taylor expansion to rigorously bridge the post-tuning mechanistic objective with the pre-SFT model's dynamic gradients. Practically, we design dual-granularity (neuron- and component-level) localization pipelines. Extensive experiments demonstrate that our approach not only provides superior SFT guidance but also exhibits robust performance and temporal scalability across increasing model sizes. This work transcends the fundamental limitation of traditional interpretability-its inability to identify task-critical mechanisms before they are trained-pioneering a predictive frontier that unites mechanistic interpretability with targeted optimization.