Layer 8 · Neuron 8124 · boosted

L8N8124+1

Word quirks:

“ my”“ typical”“ typically”“ myself”“ example”“ usually”“ personal”“ usual”

💤 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 an AI assistant designed to provide helpful information. My primary mission is to assist users with their tasks while maintaining a safe, respectful, and productive environment. If you have specific goals or challenges, feel free to share them so I can tailor my approach accordingly.

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. L9N4951+1🕒	0.93	“ usually”“ usual”“ typical”
2. L8N3865-1🕒	0.93	“ myself”“ usual”“ normally”
3. L8N6419+1💤	0.92	“ typically”“ typical”“ often”
4. L8N9036+1🕒	0.91	“ typical”“ typically”“ standard”
5. L10N8716-1🕒	0.91	“ typically”“ my”“ usually”
6. L11N3120-1🕒	0.91	“ normally”“ generally”“ ordinarily”
7. L7N7630-1💤	0.90	“ usual”“ usually”“ myself”
8. L9N7484-1💤	0.90	“ typical”“ usually”“ now”
9. L16N3458+1💤	0.88	“ itself”“ typical”“ usual”
10. L12N8399+1💤	0.88	“ sometimes”“ my”“ typical”

Shadow specimen, apart from the ten: L8N8124-1💤, -0.13.

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 8124, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.59, top-1 agreement 0.72) 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
L8N8124+1 t0-v0.1	0.588	0.72	0.821	1.28	Top boosted tokens ↑
L8N8124-1💤 shadow specimen t0-v0.1	0.888	0.64	0.960	1.23	“ *“”“ “”“ ‘”“ “”“ **‘”““”“ (“”“‘”

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.