INDEX

Explanations

references to the interplay between religion and government

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

lixir

-0.14

ascade

-0.13

ê·Ģ

-0.12

æĢ

-0.12

redits

-0.12

urse

-0.12

 Patriots

-0.12

 gravel

-0.12

ettle

-0.12

 Monsters

-0.12

POSITIVE LOGITS

 religion

0.56

 religious

0.56

 church

0.55

 relig

0.52

 Religious

0.50

 Religion

0.50

 Church

0.48

church

0.46

 churches

0.46

religious

0.45

Activations Density 1.507%

references to the interplay between religion and government

No Comments

No Known Activations