Layer 8 · Neuron 996 · boosted

L8N996+1

Word quirks:

“ separate”“<|im_end|>”“ separately”“ specially”“ special”“ particular”“ usually”“ ONLY”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

As an AI, I don't have a personal mission, but I can certainly help you understand the broader context by analyzing patterns across different domains. My role is to ensure that the knowledge I provide is consistent with the specific needs of each user, even if I don't explicitly state them. This is where my strength lies in terms of generalization.

For example, if you're asking about coding, I can provide insights into how that applies to other areas like web development or mobile apps. Similarly, if you're interested in data analysis, I can offer guidance on how that translates to other contexts like **

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. L8N2177-1💤	0.87	“ separate”“ usually”“ special”
2. L12N6226-1🕒	0.86	“ specific”“ different”“ differently”
3. L11N8065-1🕒	0.85	“ specially”“ seperate”“ separate”
4. L11N6955+1🕒	0.85	“ specially”“ special”“ now”
5. L11N8925+1🕒	0.84	“ specifically”“ specific”“ standalone”
6. L14N7242-1💤	0.84	“ separate”“ separately”“ independently”
7. L10N7347+1💤	0.83	“ specially”“ ONLY”“ completely”
8. The Hollow Specialist✅ L12N9188-1	0.82	“ specific”“<\|im_end\|>”“ specialized”
9. L11N8381+1💤	0.82	“ this”“ particular”“ now”
10. L10N9208+1🕒	0.82	“ special”“ specially”“ particular”

Shadow specimen, apart from the ten: L8N996-1💤, -0.18.

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 996, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.52, top-1 agreement 0.47) 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
L8N996+1 t0-v0.1	1.515	0.47	1.861	1.85	Top boosted tokens ↑
L8N996-1💤 shadow specimen t0-v0.1	0.880	0.62	1.145	1.61	“ \"”“ "”“ “”“ "”“ "”“ "”“ “”“ *“”

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.