INDEX

Explanations

references to political policies and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

azen

-0.17

 çĶŁåĳ½åĳ¨æľŁåĩ½æķ°

-0.15

Î¼Î¹

-0.15

arih

-0.15

itzerland

-0.14

 abandonment

-0.14

aal

-0.14

Î»Î¹

-0.14

 sexism

-0.14

ToList

-0.14

POSITIVE LOGITS

 freedom

0.27

 Freedom

0.23

 freedoms

0.22

 censorship

0.20

 liberty

0.20

Freedom

0.20

fre

0.19

 regime

0.19

 freely

0.19

fre

0.18

Activations Density 0.172%

references to political policies and their implications

No Comments

No Known Activations