How does representation geometry causally drive model behavior?

The central scientific question the paper addresses through the lens of interventional causality.

Source paper

extracted_from

Steering Along Manifolds to Control Neural Networks

Neighborhood — ranked by edge-count

Papers (1)

paper

Steering Along Manifolds to Control Neural Networks
introduces

Findings (1)

finding

The representation-based path and the behavior-based path in Llama-3.1 8B activation space trace out similar curves, demonstrating bidirectional geometry alignment.
answered_by
Key empirical result showing that optimizing for behavioral outputs and fitting representation geometry produce the same path in activation space.

Claims (1)

claim

The geometry of internal representations and the geometry of model behavior share a precise correspondence — representation geometry is a window into the inner world of neural networks.
gates
The paper's deepest interpretive claim, asserting that representation structure and behavioral structure are not coincidentally aligned but deeply connected.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

We hypothesize that representation geometry drives model behavior — the geometric structure of internal representations causally shapes what models do externally.hypothesis0.907
The causal hypothesis motivating the use of causality (intervention) as the lens connecting representation and behavior geometry.
causal shaping of behavior by representation geometryconcept0.864
Central question: does geometry in activation space causally determine behavior?
Representation geometry causally shapes behavior; activation and behavior manifolds are approximately isometric.claim0.864
Does the geometric structure of neural representations causally shape model behavior?question0.858
The motivating research question of the paper
Geometric structure of neural representations causally shapes model behaviorclaim0.844
The paper's core causal assertion: geometry is not incidental but mechanistically linked to behavior
Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.840
Central hypothesis tested via manifold steering experiments across language models and video world models.
There is a clear bidirectional relationship between the geometry of behavior and representation: steering along representation manifolds follows behavior manifolds, and vice versa.claim0.839
The paper's finding that the alignment holds in both directions — from representation to behavior and from behavior back to representation space.
There is a bidirectional relationship between the geometry of representation and behavior across tasks and modalities.claim0.832
Author’s interpretive claim that the shared geometry is general and robust.