# Sparse Activation Editing for Reliable Instruction Following in Narratives

arXiv: https://arxiv.org/abs/2505.16505 · HTML: https://mlsanity.com/paper/2505.16505/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://mlsanity.com/paper/2408.05147/) (2024)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback](https://mlsanity.com/paper/2306.14898/) (2023)
- [Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders](https://mlsanity.com/paper/2410.20526/) (2024)
- [Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering](https://mlsanity.com/paper/2410.15999/) (2024)
- [Learning to Edit: Aligning LLMs with Knowledge Editing](https://mlsanity.com/paper/2402.11905/) (2024)
- [Low-Rank Adaptation for Foundation Models: A Comprehensive Review](https://mlsanity.com/paper/2501.00365/) (2024)
- [SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models](https://mlsanity.com/paper/2502.11356/) (2025)
- [RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following](https://mlsanity.com/paper/2502.11387/) (2025)
- [PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games](https://mlsanity.com/paper/2404.17662/) (2024)
- [An Automated Explainable Educational Assessment System Built on LLMs](https://mlsanity.com/paper/2412.13381/) (2024)

## Built on by (most cited first, 4 of 4)

- [Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement](https://mlsanity.com/paper/2509.23799/) (2025)
- [Iterative Multilingual Spectral Attribute Erasure](https://mlsanity.com/paper/2506.11244/) (2025)
- [Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles](https://mlsanity.com/paper/2606.12088/) (2026)
- [Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility](https://mlsanity.com/paper/2610.20139/) (2026)

## Abstract (arXiv)

Complex narrative contexts often challenge language models' ability to follow instructions, and existing benchmarks fail to capture these difficulties. To address this, we propose Concise-SAE, a training-free framework that improves instruction following by identifying and editing instruction-relevant neurons using only natural language instructions, without requiring labelled data. To thoroughly evaluate our method, we introduce FreeInstruct, a diverse and realistic benchmark of 1,212 examples that highlights the challenges of instruction following in narrative-rich settings. While initially motivated by complex narratives, Concise-SAE demonstrates state-of-the-art instruction adherence across varied tasks without compromising generation quality.