INDEX

Explanations

mentions of women and gender-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

;width

-0.25

 writer

-0.21

 Woman

-0.20

 woman

-0.20

,width

-0.20

(writer

-0.20

 Womens

-0.19

 writers

-0.19

 wrists

-0.19

 ÙĪÙĦÙĬ

-0.19

POSITIVE LOGITS

unw

0.21

 monthly

0.18

men

0.18

 girls

0.17

Month

0.17

-linux

0.16

-month

0.16

 months

0.16

 Monthly

0.16

 girl

0.16

Activations Density 0.089%

mentions of women and gender-related topics

No Comments

No Known Activations