INDEX

Explanations

acetylcholine

np_max-act · gemini-2.0-flash

This neuron activates on mentions of cholinergic/acetylcholine-related terms (e.g., “acetylcholine,” “cholinergic”).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 DEVELO

-0.07

ede

-0.07

 theatre

-0.07

 verwenden

-0.06

 neutrality

-0.06

 прик

-0.06

 اینترنتی

-0.06

herence

-0.06

EDI

-0.06

 electrodes

-0.06

POSITIVE LOGITS

 लड़क

0.07

koa

0.06

 φω

0.06

Trail

0.06

_response

0.06

ービス

0.06

ยนต

0.06

Party

0.06

 बनन

0.06

ools

0.06

Activations Density 0.007%

acetylcholine

This neuron activates on mentions of cholinergic/acetylcholine-related terms (e.g., “acetylcholine,” “cholinergic”).

No Comments

No Known Activations