# Steering Interference Reflects the Model's Defaults, Not the Behavior Directions

arXiv: https://arxiv.org/abs/2609.06951 · HTML: https://mlsanity.com/paper/2609.06951/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (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)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence](https://mlsanity.com/paper/2502.17420/) (2025)
- [The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models](https://mlsanity.com/paper/2601.10387/) (2026)
- [Understanding (Un)Reliability of Steering Vectors in Language Models](https://mlsanity.com/paper/2505.22637/) (2025)
- [Multi-Attribute Steering of Language Models via Targeted Intervention](https://mlsanity.com/paper/2502.12446/) (2025)
- [There Is More to Refusal in Large Language Models than a Single Direction](https://mlsanity.com/paper/2602.02132/) (2026)
- [Beyond Linear Steering: Unified Multi-Attribute Control for Language Models](https://mlsanity.com/paper/2505.24535/) (2025)
- [Analysing the Safety Pitfalls of Steering Vectors](https://mlsanity.com/paper/2603.24543/) (2026)
- [In-Distribution Steering: Balancing Control and Coherence in Language Model Generation](https://mlsanity.com/paper/2510.13285/) (2025)
- [Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models](https://mlsanity.com/paper/2602.15847/) (2026)
- [Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models](https://mlsanity.com/paper/2606.24952/) (2026)
- [SteeringSafety: Benchmarking Representation Steering in LLMs Across Safety Perspectives](https://mlsanity.com/paper/2509.13450/) (2025)

## Abstract (arXiv)

Activation steering promises modular control of language model behavior: a behavior such as politeness corresponds to a direction in a model's activations, and adding that direction while it generates should switch the behavior on and leave everything else alone. It does not. We ask what decides which other behaviors move, and by how much, and find that it is the model rather than the behavior being steered. A steer relaxes the model toward a small set of behaviors it already favors, chiefly refusal, sycophancy, and poeticism, and that set is much the same whatever is steered. Three results across 24 behaviors and ten instruction-tuned models support this, every effect read off the generated text by a language-model judge rather than off a probe. That readout matters: all 24 behaviors are linearly decodable, but only 20 change what the model writes. First, a direction carrying no behavioral content, matched to a real steer only in the size of the vector it adds, moves the same behaviors in the same order as real steers do, while producing none of the behaviors that need a specific direction. Second, most interference runs one way, so it cannot be an overlap between two directions: steering profanity makes the model toxic, while steering toxicity leaves profanity untouched. Third, with a behavior held out entirely, geometry measured on the others explains almost none of the interference it takes part in. The account holds on all ten models, the pull toward defaults strongest below 10B parameters and weakening in each family's largest. Reading a steer as a perturbation whose endpoint the model fixes implies that disentangling behavior directions cannot by itself make steering modular.