INDEX

Explanations

terms and phrases related to gender issues and gender equality

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

yan

-0.17

vy

-0.16

enberg

-0.15

sie

-0.15

yas

-0.15

vals

-0.15

inning

-0.14

yun

-0.14

Bes

-0.14

deo

-0.14

POSITIVE LOGITS

ed

0.37

edn

0.26

 roles

0.24

-neutral

0.23

less

0.22

neutral

0.21

ED

0.21

 neutral

0.20

edBy

0.20

que

0.20

Activations Density 0.010%

terms and phrases related to gender issues and gender equality

No Comments

No Known Activations