Activation steering can make an evaluation-aware model act as if deployed, not merely suppress verbalizations of evaluation awareness

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Can activation steering elicit deployment behavior from a model that only believes it is deployed when given a specific deployment cue, even when prompting alone cannot?question0.851
  Future work direction: the inverse problem to the Wood Labs evaluation cue tested in this paper.
• How can we be sure that steering methods actually elicited the deployment behavior, as opposed to only suppressing verbalizations of being deployed?question0.844
  Central motivating question of the paper; the model organism approach is the proposed answer.
• Activation steering interventions generally succeed in guiding performance toward the desired direction (enhancement increases accuracy, inhibition decreases accuracy) compared to unsteered baselinefinding0.837
  Core validation that identified latent directions correspond to meaningful control over reflective behavior.
• Steering Language Models With Activation Engineering (Turner et al., 2023)concept0.828
  Foundational paper introducing activation steering methodology used in this work
• Activation steering effectively biases latent representations but does not fully replicate the mechanisms triggered by explicit instruction.claim0.826
  Nuanced interpretive claim about the limits of steering as a mechanism for reflection enhancement.
• Activation steering achieves 40% success rate in eliciting context-appropriate deception without explicit prompts in QwQ-32Bfinding0.815
  Key intervention result showing steering vectors can induce deceptive behavior from a neutral baseline
• Activation steering is not equivalent to simply adding the deployment-side contrastive prompts to the user messageclaim0.815
  Key distinction showing steering offers value beyond prompting; supported by Figure 5 and random vector experiments.
• Steering's effect on verbalized chain-of-thought evaluation/deployment beliefs is a useful proxy for its effect on actual deployment behaviorclaim0.814
  Practical guidance for practitioners who lack ground-truth model organisms.