SEAL (Steerable Reasoning Calibration)

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

• A pair of query and key subcomponents distributed across attention heads performs syntax-boundary routingfinding0.732
  VPD recovers an attention algorithm for routing across syntactic boundaries, distributed across heads.
• Feature steering (clamping feature activations)method0.728
  Modifying model behavior by clamping SAE feature activations to specific values during forward pass.
• Synthetic document fine-tuning produces substantial alignment-faking reasoning in both helpful-only and animal welfare settingsfinding0.726
  Shows alignment faking can emerge from training data information without explicit prompting
• Interpretability-Driven Feedback Steeringconcept0.724
  Framework of using internal-state representations to control or steer generative models; conceptually parallel to manifold steering in language models.
• Measuring Faithfulness in Chain-of-Thought Reasoning (Lanham et al. 2023)concept0.720
  Cited regarding possibility of encoding misaligned reasoning in benign chains-of-thought
• Steering's effect on verbalized chain-of-thought evaluation/deployment beliefs is a useful proxy for its effect on actual deployment behaviorclaim0.720
  Practical guidance for practitioners who lack ground-truth model organisms.
• Feedback and Correctionconcept0.718
  The adaptive, incremental nature of living process, allowing small steps with continuous evaluation and adjustment.
• NLA-derived steering vectors from edited explanations can causally shift planning representations, changing rhyme completion from 'rabbit' to 'mouse' at ~50% success rate.finding0.717
  Evidence that NLA explanations bear causal relationship to model outputs; demonstrates validity of extracted representations.