# Steer Like the LLM: Activation Steering that Mimics Prompting

arXiv: https://arxiv.org/abs/2605.03907 · HTML: https://mlsanity.com/paper/2605.03907/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 31 of its 37 references that are in the map.
- First posted on arXiv 5 May 2026.

## Placed in

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

## Builds on (most cited first, 30 of 31)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [Foundational Challenges in Assuring Alignment and Safety of Large Language Models](https://mlsanity.com/paper/2404.09932/) (2024)
- [Improving Instruction-Following in Language Models through Activation Steering](https://mlsanity.com/paper/2410.12877/) (2024)
- [Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information](https://mlsanity.com/paper/1808.08079/) (2018)
- [Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors](https://mlsanity.com/paper/2410.12299/) (2024)
- [Counterfactuals uncover the modular structure of deep generative models](https://mlsanity.com/paper/1812.03253/) (2018)
- [Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks](https://mlsanity.com/paper/2411.16721/) (2024)
- [Multi-Attribute Steering of Language Models via Targeted Intervention](https://mlsanity.com/paper/2502.12446/) (2025)
- [Learning without training: The implicit dynamics of in-context learning](https://mlsanity.com/paper/2507.16003/) (2025)
- [Discovering the Compositional Structure of Vector Representations with Role Learning Networks](https://mlsanity.com/paper/1910.09113/) (2019)
- [To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models](https://mlsanity.com/paper/2510.13290/) (2025)
- [Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering](https://mlsanity.com/paper/2511.00617/) (2025)
- [Beyond Linear Steering: Unified Multi-Attribute Control for Language Models](https://mlsanity.com/paper/2505.24535/) (2025)
- [HyperSteer: Activation Steering at Scale with Hypernetworks](https://mlsanity.com/paper/2506.03292/) (2025)
- [Improved Representation Steering for Language Models](https://mlsanity.com/paper/2505.20809/) (2025)

## Built on by (most cited first, 5 of 5)

- [Constitutional adapters: Inference-time interventions for misalignment and misuse](https://mlsanity.com/paper/2609.36657/) (2026)
- [First-Order Steering: Translating Weight Adaptation into Activation Steering](https://mlsanity.com/paper/2610.04283/) (2026)
- [One Token Can Be Enough: Bridging Prompting and Activation Steering with Prefix Steering](https://mlsanity.com/paper/2610.04967/) (2026)
- [Backdooring Sparse Autoencoders](https://mlsanity.com/paper/2610.06049/) (2026)
- [Not All Drift Is a Mechanism: Tracing Prompt Adaptation in LLMs](https://mlsanity.com/paper/2610.18412/) (2026)

## Abstract (arXiv)

Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt steering as a form of activation steering and investigates whether distilling successful prompt steering behavior into simpler, interpretable models can close this gap. Our analysis reveals that popular activation steering methods are not faithful to the mechanics of prompt steering, which applies strong interventions on some tokens while barely affecting others. Based on these insights, we introduce Prompt Steering Replacement (PSR) models that estimate token-specific steering coefficients from the activations themselves and are trained to imitate prompt-based interventions. Experiments on three steering benchmarks across multiple language models show that PSR models outperform existing activation steering methods, especially when controlling for high-coherence completions, and also compare favorably to prompting on AxBench and persona steering.