INDEX

Explanations

Smoking

np_max-act · gemini-2.0-flash

This neuron fires on mentions of smoking and tobacco‐use terms (e.g. “smoking,” “smokers,” “tobacco”).

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

 tech

-0.07

antu

-0.07

Api

-0.07

 حسن

-0.06

 کیفیت

-0.06

倉

-0.06

 BaseService

-0.06

 Tech

-0.06

ultan

-0.06

Fetcher

-0.06

POSITIVE LOGITS

 smoking

0.10

 Smoking

0.10

мер

0.07

smo

0.07

sme

0.06

ScreenWidth

0.06

ming

0.06

StrLn

0.06

])):↵

0.06

')])↵

0.06

Activations Density 0.006%

Smoking

This neuron fires on mentions of smoking and tobacco‐use terms (e.g. “smoking,” “smokers,” “tobacco”).

No Comments

No Known Activations