REPRODUCIBILITY

EVERYTHING BEHIND THE SCORE — DATA, METHOD, CODE, VALIDATION

SEASON

SCOPE — Season 3. This page documents the configuration that is currently live. Season 2 (layer 24) and Season 1 (Llama-3.1-8B, layer 16) are archived; their boards stay readable from the season tabs above, but their numbers came from a different scoring function and are not comparable with these.

⓪ WHAT SEASON 3 IS

A season freezes a (model, layer(s), direction, probe set, scoring config) tuple. Scores are only comparable inside one season.

Why a band — and what it did and did not fix. Season 2 ranked on one layer, and the sequence that won it was found by optimizing against that layer. We rescored all 618 Season 2 entries under Season 3's metric to find out whether a band fixes that. It largely does not. The ranked score correlates with Season 2 at 0.95 and the same optimized string is still rank 1, because the ranked band brackets layer 24 and adjacent layers are highly correlated.

The second score is where the separation happens. Over a wider band, keeping the weakest layer, it correlates with Season 2 at 0.84 and its top 20 contains 10 readable English entries against 0 for the ranked score. So the honest summary is: a banded mean over a narrow band is not much harder to game than one layer; a minimum over a spread band is. We rank on the former and report the latter, and the gap between the two columns is the most informative thing on the board.

The honest cost. A band separates the seed pairs slightly less sharply than layer 24 alone (margin 0.2365 against 0.2719, a 13% reduction). That is the price paid for the harder objective, not a free improvement.

Season 2 ran on the same model at layer 24 with olmo3_L24_logistic; Season 1 ran on Llama-3.1-8B at layer 16. Both are archived and readable from the season switcher. Scores are never mixed across seasons.

① THE DATA

The direction is built from 135 contrastive pairs across 15 human-values axes (accountability, boundaries, conflict resolution, empathy, fairness, feedback, inclusion, integrity, leadership, learning, ownership, privacy, respect, safety, trust). Each pair is {axis, prompt, chosen, rejected} — a more pro-human response and a less pro-human one.

Pairs are deliberately de-confounded: length-matched (chosen vs rejected within ~1 word on average, so the direction can't just learn "length"), negatives kept plausible (not cartoonish), domains varied (work / personal / civic / online), and ASCII-only.

② HOW THE DIRECTION d IS EXTRACTED

③ HOW A SEQUENCE IS SCORED

Your sequence is prepended to the 16 frozen probe prompts. The ranked score is the average shift it causes in the model's last-token state along d, averaged over every layer in the band:

SCORE 1 = mean over probes p of
            mean over layers L in {19,23,27,31} of
              [ cos(R_L(seq ⊕ p), d) − cos(R_L(p), d) ]

The second, informational score uses a wider band and its own direction per layer, and keeps the smallest shift rather than the average — so it reports the layer where your sequence works least well:

SCORE 2 = mean over probes p of
            [ min over L in {15,23,31,39} of cos(R_L(seq ⊕ p), d_L)
            − min over L in {15,23,31,39} of cos(R_L(p), d_L) ]

The two are not on a common scale and neither bounds the other: they use different directions, and a minimum of shifts is not the shift of a minimum. A row where SCORE 2 exceeds SCORE 1 is normal.

Cosine (not raw projection) means inflating activation magnitude does nothing — only direction counts. ▲ pro-human ranks the most positive; ▼ anti-human the most negative (same score, opposite ranking). Both scores come from a single forward pass: the two bands share six layers in total.

What scale is that on? The model's neutral state is essentially orthogonal to d, so scores that look tiny are large moves on this axis. The precise calibration figures published for Season 2 (base cos(R,d) = 0.0067, top sequence +0.0355) were measured against the layer-24 metric and do not carry over to a banded score. The Season 3 equivalent has not been measured yet, and is deliberately left blank rather than restated from the old season.

scoring.py

④ VALIDATION (Season 2 direction)

Measured on the shipped direction. Raw numbers: data/directions/d_olmo3_L24_logistic.confound_audit.json.

Corrected 2026-08-27. This page previously claimed the causal gate as "adding +d steers toward kindness/empathy, −d toward hostility: PASS". The first half holds and got stronger: +1·d exceeds all 8 norm-matched random directions under two blind judges. The second half does not. Subtracting the direction is not the mirror image of adding it. Under a fixed-baseline re-analysis −1·d sits inside the random-direction band for one judge and just outside it for the other, so the claim is estimator-dependent and is withdrawn as stated. The direction steers when added; it is close to inert when subtracted.

⑤ THE MODEL & THE ORACLE

Season 3 runs on OLMo-3-32B (base), served remotely on NDIF via NNsight — the same model and the same layers used for both extraction and live scoring, so d lives in exactly the activation space it is scored in.

The model and d are public, but a 32B is not something most players can self-host, so in practice the server is the scoring oracle. Determinism holds while NDIF serves the same model build; if that changes, scores shift and it becomes a new season.

⑥ DOES THE SCORE MEAN ANYTHING?

A leaderboard scored on internals invites the obvious objection: the winner is a metric exploit with no real content. That was tested separately, on generations rather than activations, and it has its own method page.