INDEX

Explanations

references to gender roles and equity issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

uhe

-0.18

ahoma

-0.15

utsch

-0.15

à¸£à¸ĵ

-0.15

à¸Ńà¸Ķ

-0.15

Kid

-0.14

pai

-0.14

fon

-0.14

(*)(

-0.14

ItemSelectedListener

-0.14

POSITIVE LOGITS

 women

0.71

 females

0.57

women

0.56

men

0.54

 girls

0.54

 woman

0.50

 ladies

0.49

 Women

0.49

 female

0.48

Women

0.48

Activations Density 0.298%

references to gender roles and equity issues

No Comments

No Known Activations

references to gender roles and equity issues

No Comments

No Known Activations