Neural Steering Methods

Frontmatter (5 fields)

{
  "label": "Neural Steering Methods",
  "corpus": "papers",
  "graph_path": "/Users/antonborzov/Documents/Research.nosync/papers/graphify-out/graph.json",
  "node_count": 18,
  "community_index": 2
}

Outgoing (0)

None.

Incoming (18)

Members (18)

Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts(paper)
Attention probes for belief decoding(concept)
Chain-of-Thought Reasoning(concept)
Circular Representations(concept)
Data Attribution(concept)
Distractor-Triggered Compliance(concept)
Goodfire AI research collective(concept)
Llama-3.1 8B(concept)
Manifold steering for neural network control(concept)
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior(paper)
Mechanistic Interpretability(concept)
OLMo 2(concept)
Performative chain-of-thought(concept)
Probe-based data attribution for alignment(concept)
Probe-Based Data Attribution: Surfacing and Mitigating Undesirable Behaviors in LLM Post-Training(paper)
+3 more