# Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods

arXiv: https://arxiv.org/abs/2610.07722 · HTML: https://mlsanity.com/paper/2610.07722/

## 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 21 of its 63 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Towards Unifying Interpretability and Control: Evaluation via Intervention](https://mlsanity.com/paper/2411.04430/) (2024)
- [HyperSteer: Activation Steering at Scale with Hypernetworks](https://mlsanity.com/paper/2506.03292/) (2025)
- [Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models](https://mlsanity.com/paper/2602.01654/) (2026)
- [Curveball Steering: The Right Direction To Steer Isn't Always Linear](https://mlsanity.com/paper/2603.09313/) (2026)
- [Contextual Linear Activation Steering of Language Models](https://mlsanity.com/paper/2604.24693/) (2026)
- [Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention](https://mlsanity.com/paper/2605.05892/) (2026)
- [Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency](https://mlsanity.com/paper/2603.12298/) (2026)
- [ORBIT: Training-Free Multi-Attribute Behavioral Steering via Orthogonal Subspace Rotation](https://mlsanity.com/paper/2606.22357/) (2026)
- [Mind the Performance Gap: Capability-Behavior Trade-offs in Feature Steering](https://mlsanity.com/paper/2602.04903/) (2026)
- [Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior](https://mlsanity.com/paper/2606.08454/) (2026)
- [FaithSteer-BENCH: A Deployment-Aligned Stress-Testing Benchmark for Inference-Time Steering](https://mlsanity.com/paper/2603.18329/) (2026)
- [UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering](https://mlsanity.com/paper/2605.30076/) (2026)
- [Conditional Optimal Bridge for Riemannian Activation Steering](https://mlsanity.com/paper/2607.10517/) (2026)
- [Manifold-Guided Attention Steering](https://mlsanity.com/paper/2605.21770/) (2026)
- [High-Dimensional Random Projection for Activation Steering in Language Models](https://mlsanity.com/paper/2606.15092/) (2026)

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

- [Beyond Bias Scores: Answerability Confounds in Activation Steering with Gradient-Constrained Direction Design (GCD)](https://mlsanity.com/paper/2610.17641/) (2026)

## Abstract (arXiv)

Activation steering provides a lightweight and flexible way to control large language model (LLM) behavior. However, effective steering requires more than inducing the intended behavior: it should also limit unintended changes and remain robust across inputs and training data. Existing evaluations cover these dimensions only in fragments. As a result, the trade-offs between efficacy and side effects have not been systematically characterized. We introduce SteerScope, a two-axis, multi-dimensional evaluation suite that jointly characterizes steering outcomes and method properties through 15 metrics. We score target efficacy and side effects on language quality, task capabilities, and safety and reliability, and further assess generalization and data dependence through steering-specific metrics for sample efficiency and sample sensitivity. Rather than comparing methods at a single operating point, we characterize the trade-offs between efficacy and side effects. Under matched models, tasks, and evaluation protocols, we benchmark 23 methods spanning 4 families, including prompting, LoRA, and SFT as baseline methods, and release the suite as an extensible codebase. We find that current activation steering methods do not yet surpass the Prompt Steering baseline in their overall balance between steering efficacy and side effects: across both model scales, no evaluated activation steering method achieves higher efficacy without incurring greater composite side effects. We further uncover a consistent coupling between steering efficacy and side effects. Under OOD prompts, target efficacy is often preserved, whereas side effects tend to become more pronounced, particularly through declines in instruction relevance and fluency. Methods also exhibit sharply different sample-efficiency profiles.