# Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal

arXiv: https://arxiv.org/abs/2608.24988 · HTML: https://mlsanity.com/paper/2608.24988/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Not All Language Model Features Are One-Dimensionally Linear](https://mlsanity.com/paper/2405.14860/) (2024)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling](https://mlsanity.com/paper/2312.15166/) (2023)
- [Catastrophic Failure of LLM Unlearning via Quantization](https://mlsanity.com/paper/2410.16454/) (2024)
- [Robust LLM safeguarding via refusal feature adversarial training](https://mlsanity.com/paper/2409.20089/) (2024)
- [Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation](https://mlsanity.com/paper/2410.03415/) (2024)
- [An Embarrassingly Simple Defense Against LLM Abliteration Attacks](https://mlsanity.com/paper/2505.19056/) (2025)
- [Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility](https://mlsanity.com/paper/2507.11630/) (2025)
- [Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection](https://mlsanity.com/paper/2508.20766/) (2025)

## Built on by (most cited first, 1 of 1)

- [When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety](https://mlsanity.com/paper/2609.34771/) (2026)

## Abstract (arXiv)

Activation steering can be embedded directly into a language model's weights, shaping behaviour without inference-time intervention and offering a way to encode alignment prior to release. However, models are routinely fine-tuned after deployment, and it is unknown whether embedded interventions survive this. We study the stability of embedded steering for refusal ablation and brevity amplification across five instruction-tuned models (3B-14B) under non-adversarial SFT and RLHF. We find that steering degrades more under stronger optimisation pressure against the steered behaviour, which depends on both the training data and the training algorithm. Refusal ablation loses 69% of its effect on average under our SFT setup, but only 2% under our RLHF setup. The weight-edit, by contrast, remains almost unchanged (on average only 0.4% of it is restored), and the fine-tuning update along the steering direction is close to orthogonal to the pre-edit weight pattern (mean cosine similarity 0.071). Fine-tuning that restores the behaviour does so without reversing the edit. As the steered behaviour is not fully durable, embedded steering should be re-validated after downstream training.