INDEX

Explanations

references to body image issues and societal expectations related to beauty

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post

Features

65,536

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

gated

Context Size

1,024

Dataset

Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mux

-0.17

aget

-0.15

utherland

-0.15

 homosexual

-0.14

bere

-0.14

 báº¡c

-0.14

AREST

-0.14

RARY

-0.13

MUX

-0.13

wat

-0.13

POSITIVE LOGITS

 body

0.43

 beauty

0.39

 Body

0.37

fat

0.33

 Beauty

0.32

Body

0.32

 weight

0.32

 BODY

0.31

-body

0.30

 bodies

0.30

Activations Density 0.073%

references to body image issues and societal expectations related to beauty

No Comments

No Known Activations