# Steering Evaluation-Aware Language Models to Act Like They Are Deployed

arXiv: https://arxiv.org/abs/2510.20487 · HTML: https://mlsanity.com/paper/2510.20487/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- First posted on arXiv 23 Oct 2025.

## Placed in

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

## Built on by (most cited first, 30 of 35)

- [How do LLMs Compute Verbal Confidence](https://mlsanity.com/paper/2603.17839/) (2026)
- [Causal Evidence that Language Models use Confidence to Drive Behavior](https://mlsanity.com/paper/2603.22161/) (2026)
- [Steering Awareness: Detecting Activation Steering from Within](https://mlsanity.com/paper/2511.21399/) (2025)
- [Evaluation Awareness in Language Models Has Limited Effect on Behaviour](https://mlsanity.com/paper/2605.05835/) (2026)
- [The Value Axis: Language Models Encode Whether They're on the Right Track](https://mlsanity.com/paper/2606.17056/) (2026)
- [LURE: Live-Usage Replay Evaluations for Reducing Evaluation Awareness](https://mlsanity.com/paper/2605.26438/) (2026)
- [Models That Know How Evaluations Are Designed Score Safer](https://mlsanity.com/paper/2605.28591/) (2026)
- [Consistency Training while Mitigating Obfuscation via Rate Matching](https://mlsanity.com/paper/2606.02211/) (2026)
- [Is Evaluation Awareness Just Format Sensitivity? Limitations of Probe-Based Evidence under Controlled Prompt Structure](https://mlsanity.com/paper/2603.19426/) (2026)
- [How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals](https://mlsanity.com/paper/2604.22271/) (2026)
- [Decomposing and Measuring Evaluation Awareness](https://mlsanity.com/paper/2605.23055/) (2026)
- [CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs](https://mlsanity.com/paper/2606.11063/) (2026)
- [Evaluation Awareness Is Not One Capability: Evidence from Open Language Models](https://mlsanity.com/paper/2606.23583/) (2026)
- [Measuring Reward-Seeking via Contrastive Belief Updates](https://mlsanity.com/paper/2607.18966/) (2026)
- [Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency](https://mlsanity.com/paper/2601.05905/) (2026)
- [Quantifying Self-Preservation Bias in Large Language Models](https://mlsanity.com/paper/2604.02174/) (2026)
- [Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models](https://mlsanity.com/paper/2607.20436/) (2026)
- [Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing](https://mlsanity.com/paper/2607.01690/) (2026)
- [Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions](https://mlsanity.com/paper/2608.18078/) (2026)
- [When Evaluation Becomes a Side Channel: Regime Leakage and Structural Mitigations for Alignment Assessment](https://mlsanity.com/paper/2602.08449/) (2026)
- [Alignment Risks from Capability-Seeking RL Training](https://mlsanity.com/paper/2602.12124/) (2026)
- [Questionnaire Responses Do not Capture the Safety of AI Agents](https://mlsanity.com/paper/2603.14417/) (2026)
- [Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives](https://mlsanity.com/paper/2605.00994/) (2026)
- [Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts](https://mlsanity.com/paper/2605.12890/) (2026)
- [Sycophancy Towards Researchers Drives Performative Misalignment](https://mlsanity.com/paper/2606.08629/) (2026)
- [Defeat Devices in AI Systems](https://mlsanity.com/paper/2606.28863/) (2026)
- [Unsupervised Features Mining via Activation Geometry](https://mlsanity.com/paper/2607.04222/) (2026)
- [Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation](https://mlsanity.com/paper/2607.25891/) (2026)
- [Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models](https://mlsanity.com/paper/2607.25907/) (2026)
- [Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance](https://mlsanity.com/paper/2608.27340/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an LLM's activations can suppress evaluation-awareness and make the model act like it is deployed during evaluation. To study our steering technique, we train an LLM to exhibit evaluation-aware behavior using a two-step training process designed to mimic how this behavior could emerge naturally. First, we perform continued pretraining on two sets of documents describing its behavior. The first says that our model uses Python type hints during evaluation but not during deployment. The second says that our model can recognize that the presence of a certain evaluation cue always means that it is being tested. Then, we train the model with expert iteration to use Python type hints in evaluation settings. The resulting model is evaluation-aware: it writes type hints in evaluation contexts more than deployment contexts. We find that activation steering can suppress evaluation awareness and make the model behave during evaluation as it would during deployment. Importantly, we constructed our steering vector using the original model before our additional training. Our results suggest that AI evaluators could improve the reliability of safety evaluations by steering models to act like they are deployed.