finding

active

finding:linear-steering-on-llama-3-1-8b-for-the-days-of-week-task-cuts-across-the-behavior-manifold-producing-noisy-off-target-effects-where-predicted-tokens-are-not-even-days-of-the-week

Linear steering on Llama-3.1 8B for the days-of-week task cuts across the behavior manifold, producing noisy off-target effects where predicted tokens are not even days of the week.

Empirical result demonstrating the failure mode of linear steering when concept geometry is cyclic.

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

Claims (2)

claim

Steering along manifolds provides better control than linear steering when the concept geometry is non-linear.
associated_withsupports
The central thesis of the paper, motivating the shift from linear to geometry-aware manifold steering.
Linear steering is often mismatched with a model's internal representation geometry, producing noisy, off-target effects.
supports
The paper's critique of the standard linear steering baseline, supported by the days-of-week demo.

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.

Steering Llama-3.1 8B along the circular representation manifold produces outputs that follow the natural circle of the behavior manifold, cleanly shifting probability mass from Monday through successive days.finding0.857
Core empirical result demonstrating that manifold steering produces on-target, behavior-aligned outputs.
Linear steering produces noisy off-target effects; manifold steering cleanly shifts probability mass between sequential concepts.finding0.838
Core empirical claim comparing steering approaches on cyclic concepts.
Llama-3.1 8B output token distributions for seven days of the week form seven clusters in a rough circle in behavior space (Hellinger distance geometry).finding0.832
Empirical observation establishing that Llama's behavior for days-of-week tasks has circular structure.
manifold steering produces clean probability shifts along natural behavior structure; linear steering cuts across manifold and produces off-target noisy effectsfinding0.811
Empirical demonstration on Llama-3.1-8B that steering along representation manifold aligns outputs with behavior manifold, whereas linear steering does not.
Llama-3.3-70B corrected response scores 75/100 rather than 100 due to residual steering effects (Snell's law reference)finding0.800
Illustrative finding that ESR mitigates but does not fully eliminate steering influence
Linear steering cuts through off-manifold regions and hence produces unnatural outputs.claim0.800
Attribution of failure to Euclidean assumption.
Llama-3.1 8B internal representations for the seven days of the week form seven clusters in a circle in activation space.finding0.790
Empirical observation establishing that Llama's internal representations for days-of-week have circular geometric structure.
Llama 3.3 70B is the most likely to take on a non-Assistant persona when steered, with even split between human and nonhuman portrayalsfinding0.788
Model-specific difference in persona susceptibility