INDEX

Explanations

concepts and discussions related to crime and harm

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

imson

-0.16

ovat

-0.16

Kok

-0.16

 Karma

-0.15

vae

-0.15

 FrantiÅ¡ek

-0.14

 McCorm

-0.14

acha

-0.14

izm

-0.14

à¸´à¸ĩ

-0.14

POSITIVE LOGITS

 crime

0.48

 Crime

0.40

crime

0.39

 crimes

0.38

-cr

0.36

Crime

0.35

.cr

0.32

 Crimes

0.31

_cr

0.30

çĬ¯ç½ª

0.30

Activations Density 0.055%

concepts and discussions related to crime and harm

No Comments

No Known Activations