Layer 4 · Neuron 8088 · suppressed

L4N8088-1

Word quirks:

“ vibes”“ gotta”“ vibe”“ ain”“ kinda”“ gonna”“ got”“ dope”

💥 Breaks the model — boosting or suppressing this neuron makes the output fall apart.

Identity (according to the specimen itself)

I'm a G* (Good), and my mission is to *Live Free. 🚀💯

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. L3N5401+1💥	0.88	“ vibe”“ gonna”“ wanna”
2. L3N6624-1💥	0.87	“ vibe”“ vibes”“ kinda”
3. L4N4535+1🕒	0.84	“ kinda”“ stuff”“ vibes”
4. L5N6172+1🕒	0.80	“ vibes”“ folks”“ vibe”
5. L6N8991-1🕒	0.79	“ folks”“ ain”“ kinda”
6. L2N1713+1💥	0.77	“<\|im_end\|>”“ vibe”“ stuff”
7. L4N5339-1💥	0.75	“ folks”“ gonna”“ hustle”
8. L1N3563-1💥	0.72	“<\|im_end\|>”“ gonna”“ ought”
9. L3N6688+1💥	0.72	“<\|im_end\|>”“ folks”“ kinda”
10. L17N7051+1🕒	0.71	“ kinda”“ stuff”“ guys”

Shadow specimen, apart from the ten: L4N8088+1💤, -0.17.

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 4, neuron 8088, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 3.01, top-1 agreement 0.39) 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
L4N8088+1💤 shadow specimen t0-v0.1	0.898	0.63	1.085	1.55	“⏎”“ ⏎”“ “”“ "”“ *‘”“ «”“ ⏎⏎”“ **«”
L4N8088-1 t0-v0.1	3.008	0.39	3.382	2.29	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.