# What Can We Actually Steer? A Multi-Behavior Study of Activation Control

arXiv: https://arxiv.org/abs/2511.18284 · HTML: https://mlsanity.com/paper/2511.18284/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 11 of its 13 references that are in the map.
- First posted on arXiv 23 Nov 2025.

## Placed in

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

## Builds on (most cited first, 11 of 11)

- [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)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [Improving Activation Steering in Language Models with Mean-Centring](https://mlsanity.com/paper/2312.03813/) (2023)
- [Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors](https://mlsanity.com/paper/2410.12299/) (2024)
- [Towards Reliable Evaluation of Behavior Steering Interventions in LLMs](https://mlsanity.com/paper/2410.17245/) (2024)
- [Interpretable Steering of Large Language Models with Feature Guided Activation Additions](https://mlsanity.com/paper/2501.09929/) (2025)
- [Evaluating the Prompt Steerability of Large Language Models](https://mlsanity.com/paper/2411.12405/) (2024)
- [Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks](https://mlsanity.com/paper/2411.07213/) (2024)

## Built on by (most cited first, 6 of 6)

- [Steering at the Source: Style Modulation Heads for Robust Persona Control](https://mlsanity.com/paper/2603.13249/) (2026)
- [The Cylindrical Representation Hypothesis for Language Model Steering](https://mlsanity.com/paper/2605.01844/) (2026)
- [CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse](https://mlsanity.com/paper/2607.01433/) (2026)
- [When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search](https://mlsanity.com/paper/2605.16362/) (2026)
- [Role Steering of Language Models for Social Simulations](https://mlsanity.com/paper/2608.00023/) (2026)
- [More Than Memory: Task-Conditioned Signed FFN Writes in Long-Context Retrieval](https://mlsanity.com/paper/2607.16254/) (2026)

## Abstract (arXiv)

Large language models (LLMs) require precise behavior control for safe and effective deployment across diverse applications. Activation steering offers a promising approach for LLMs' behavioral control. We focus on the question of how steering effectiveness varies across different behavior types and whether the nature of target behaviors can predict steering success. We address this through empirical analysis of activation steering across 50 behaviors that span persona archetypes, personality traits, misalignment behaviors, style cues, and impersonation of public figures. We present a set of comprehensive experiments on coefficient optimization, vector properties, and data requirements to provide comprehensive guidance for the implementation of activation steering. Our analysis demonstrates that steering effectiveness varies significantly by behavior type, with different behavioral categories exhibiting distinct response patterns to intervention strength. We find that trait expression follows an inverted-U curve with a steering coefficient strength. We also show that vector separation metrics do not predict steering success, but larger training datasets enable more aggressive steering. These findings provide empirically grounded guidance for implementing activation steering and demonstrate that steering effectiveness is heavily influenced by behavior type.