Interpretability-Driven Feedback Steering

{
  "author": null,
  "context": "Framework of using internal-state representations to control or steer generative models; conceptually parallel to manifold steering in language models.",
  "category": "ai",
  "enrichment": {
    "is_stale": true
  },
  "norm_label": "Interpretability-Driven Feedback Steering",
  "source_url": null,
  "graphify_id": "interpretability_feedback",
  "source_file": "hazra-goodfire-self-correcting-search-materials-2026.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/hazra-goodfire-self-correcting-search-materials-2026/graph.json",
  "extracted_type": "concept",
  "graphify_file_type": "concept"
}