Layer 5 · Neuron 8058 · suppressed

L5N8058-1

Word quirks:

“⏎”“<|im_end|>”“!”“!!”“ !”“ !!”“ question”“ !!!”

🕒 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)

I am a C series card.

This card belongs to the "The Sims 4" franchise, specifically the C* series, which was released in *2013.

What is this about?

In the context of The Sims 4, the C series card represents a specific milestone or achievement that players can unlock within the game. It is a way to track progress and share information between different versions of the game.

What is your mission?

In the context of The Sims 4, the mission is a specific task or objective that players can complete within

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. L1N6151-1💥	0.97	“<\|im_end\|>”“ !”“!”
2. L1N7079-1🕒	0.96	“⏎”“<\|im_end\|>”“!”
3. L2N3911+1🕒	0.96	“<\|im_end\|>”“ !!!”“!!!”
4. L1N7980-1💥	0.96	“<\|im_end\|>”“!”“?!”
5. L4N3698+1🕒	0.96	“!”“<\|im_end\|>”“ !”
6. L3N8934+1🕒	0.96	“<\|im_end\|>”“!”“⏎”
7. L4N5507+1🕒	0.96	“<\|im_end\|>”“!!”“ !!”
8. L1N7453+1💥	0.96	“<\|im_end\|>”“⏎”“!!!”
9. L3N8732+1🕒	0.96	“ !”“!”“ !!”
10. L1N3349+1💥	0.96	“<\|im_end\|>”“!”“!!”

Shadow specimen, apart from the ten: L5N8058+1💥, -0.15.

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 5, neuron 8058, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.78, 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
L5N8058+1💥 shadow specimen t0-v0.1	2.516	0.36	2.822	2.11	“ configuration”“ HTTP”“ Apache”“ config”“ XML”“ nginx”“ Configuration”“ apache”
L5N8058-1 t0-v0.1	1.781	0.47	2.132	2.30	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.