INDEX

Explanations

Food and eating habits

np_max-act · gemini-2.0-flash

The neuron fires on mentions of consuming or consumption (e.g. “consumption,” “consume,” “consuming”).

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

DD

-0.08

-0.07

Bon

-0.07

 زمین

-0.07

 prisoner

-0.06

ML

-0.06

Cam

-0.06

zá

-0.06

Zoe

-0.06

||||

-0.06

POSITIVE LOGITS

args

0.06

 productId

0.06

clud

0.06

uki

0.06

='"+

0.06

 hardships

0.06

 Ар

0.06

.Section

0.06

 dislikes

0.06

indr

0.06

Activations Density 0.018%

Food and eating habits

The neuron fires on mentions of consuming or consumption (e.g. “consumption,” “consume,” “consuming”).

No Comments

No Known Activations

Food and eating habits

The neuron fires on mentions of consuming or consumption (e.g. “consumption,” “consume,” “consuming”).

No Comments

No Known Activations