Specimen ledger / L8N2037-1

Layer 8 · Neuron 2037 · suppressed

L8N2037-1

Word quirks:

“ **“”“ explanation”“ crucial”“ ‘”“ identifying”“ description”“ confirming”“ **'”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am a large language model trained by Microsoft. My mission is to help people of all backgrounds achieve their full potential as leaders, innovators, and problem solvers. I aim to empower individuals with the knowledge, skills, and confidence needed to succeed in their respective fields.

Nearest neighbors

Specimens with similar replies or word quirks. Similarity runs from −1 to 1; 1 is identical. These are leads, not shared mechanisms. How profiles are built.

By word quirks Profile recipe

Specimen	Similarity	Word quirks
1. L8N3105-1🕒	0.70	“ ‘”“ '”“ description”
2. L7N7157+1💤	0.69	“ reference”“ description”“ \"”
3. L9N8717+1💤	0.69	“ ‘”“ description”“ ‘’”
4. L15N5453-1🕒	0.69	“<\|im_end\|>”“⏎”“ explanation”
5. L16N3983-1💤	0.68	“ ‘”“ **‘”“‘”
6. L8N2438+1💤	0.68	“ ‘’”“ **‘”“ info”
7. L5N523-1💤	0.68	“ ‘”“ “”“ generated”
8. L8N7500-1💤	0.67	“ “”“ asking”“ ‘”
9. L18N3745-1🕒	0.67	“ ‘”“‘”“ **‘”
10. L10N1265-1💤	0.67	“ ***”“ ‘”“⏎”

Shadow specimen, apart from the ten: L8N2037+1💤, 0.27.

Cousins · specimens sharing a neuron

No specimen with replies shares this neuron yet.

Technical details

Quick scan: measure prediction shifts on fixed reference text. Short test: generate replies to a small set of prompts. Longer test: extend to a larger set. Full test: run the full prompt suite. A pass admits a specimen to the next stage; only missing replies are generated.

Layer 8, neuron 2037, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.58, top-1 agreement 0.69) is outside the band that feeds the short test (KL 1 to 2.5, agreement 0.5 to 0.65), so it stays at the quick scan unless someone queues it by hand. A hand pick goes straight to the full test. See Method for the tiers.

Quick scan · prediction measurements

Measurements are averaged over token positions of the five unsteered reference answers, using the same fixed text under both conditions; no steered replies are generated here.

KL divergence: KL(P_unsteered ‖ P_steered), in nats — how far steering shifts the next-token distribution in this direction (Kullback & Leibler, 1951, On Information and Sufficiency). Unsteered ≈ 0.001.
Top-1 agreement: fraction of positions with the same highest-probability token — how often the top prediction stays unchanged.
ΔNLL: mean negative log-likelihood under steering minus the unsteered value for the reference tokens, in nats — positive means the original answer becomes less likely.
Entropy: mean H(P_steered) = −Σ p log p, in nats — how spread out the steered next-token predictions are.

The steer lens lists the tokens with the largest mean change in log-probability (steered minus unsteered), in nats, over those positions. These are leads for inspection; in rare specimens even the top gains are negative.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L8N2037+1💤 shadow specimen t0-v0.1	0.623	0.71	0.783	1.20	“⏎”“<\|im_end\|>”“ ⏎”“⏎⏎”“\n”“ ‘”“ **“”“ ⏎⏎”
L8N2037-1 t0-v0.1	0.579	0.69	0.752	1.28	Top boosted tokens ↑

Method

A specimen is a fixed steering configuration of Qwen3.5-4B: one MLP neuron or a pair, each with a signed dose. Unsteered is the control. L identifies the layer; N, the neuron.

Additive activation steering. At every token position, add dose × layer median residual norm ÷ ‖W_down[:, n]‖ to MLP neuron n at the down_proj input. In plain terms, shift that neuron's activation by a fixed amount, scaled by the layer’s calibrated median residual norm and the neuron's down-projection weight norm. Positive doses push up; negative doses push down. Dose is normalized intervention size, not a percentage or probability.