INDEX

Explanations

’s

np_max-act · gemini-2.0-flash

This neuron activates on floating‐point numbers (tokens containing decimal points).

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

 catches

-0.07

Jones

-0.07

autop

-0.07

 vocalist

-0.07

Debugger

-0.07

(gen

-0.06

мерик

-0.06

She

-0.06

pthread

-0.06

half

-0.06

POSITIVE LOGITS

 JAXB

0.06

 أم

0.06

.Lo

0.06

 नए

0.06

 المتحدة

0.06

 зн

0.06

 disregard

0.06

ีความ

0.06

 {{--<

0.06

 ContentValues

0.06

Activations Density 0.192%

’s

This neuron activates on floating‐point numbers (tokens containing decimal points).

No Comments

No Known Activations