INDEX

Explanations

references to gender and women's issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Woman

-0.26

 woman

-0.25

Woman

-0.25

woman

-0.24

 Ð¶ÐµÐ½ÑīÐ¸Ð½Ð°

-0.22

 Womens

-0.22

 Women

-0.20

 mulher

-0.19

 vrouw

-0.18

å¥³äºº

-0.18

POSITIVE LOGITS

men

0.34

-men

0.25

men

0.25

 children

0.25

Men

0.23

 gentlemen

0.23

Men

0.21

children

0.21

 Children

0.20

 hommes

0.20

Activations Density 0.029%

references to gender and women's issues

No Comments

No Known Activations