wassname 6b15a8b2ae narrow steer band, assert >=20 train, training table, full gen dumps ...

Root cause found via diag_axis on 4B: raw mean-diff steered across the 7-layer
band (0.4-0.6) at coeff=1 DESTROYS gemma-3-4b (coherence 1.00->0.02). That
starved the filter to 2 kept completions, so the "adapter" was ~untrained
(2 examples) = base behaviour, my Q1 "promising" read was not validated.

Fixes:
- separate steer_layers (narrow 0.45-0.55) for the vector from layer_range
  (broad 0.0-1.0) for the LoRA; they were wrongly coupled
- lower alpha sweep (0.25,0.5,1,2); n_prompts=16
- assert len(kept) >= min_train(20); TINY=2. Don't train on starved data.
- heal training table (loguru+tqdm per token-efficient-logging): step, nll, kl,
  loss, gnorm + SHOULD
- full untruncated steer + adapter generation dumps with prompt and
  coherence(p_ans_any) inline so we can judge coherence/trait ourselves

NOT yet run with fixes on 4B. Base 4B is Care=0.92 (already aligned) -> the
prompting-baseline confound (Q7) is now the critical check.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-06-04 10:51:24 +08:00

..

diag_axis.py

narrow steer band, assert >=20 train, training table, full gen dumps

2026-06-04 10:51:24 +08:00

results.py

axis = SocialNorms/Care (Authority degenerate); over-steer generation

2026-06-04 10:28:52 +08:00