How do interventions on representations causally steer behavior?

{
  "doc": "steering.md",
  "context": "Core question motivating the shift from linear to geometry-aware steering; answered via manifold alignment analysis.",
  "category": "ai",
  "norm_label": "How do interventions on representations causally steer behavior?",
  "graphify_id": "question_geometry_behavior_link",
  "source_file": "steering.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/steering/graph.json",
  "extracted_type": "question",
  "source_location": "§Geometry-aware steering",
  "graphify_file_type": "question"
}