INDEX

Explanations

references to criminal activity and serious offenses

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

yst

-0.16

ÅĻet

-0.16

assed

-0.14

oppel

-0.14

engu

-0.13

 caut

-0.13

ech

-0.13

Ð¸ÑģÑĤ

-0.13

.jetbrains

-0.13

Ã¼rn

-0.13

POSITIVE LOGITS

 crime

0.69

 crimes

0.59

crime

0.54

 Crime

0.53

 Crimes

0.46

Crime

0.45

 offense

0.42

 offenses

0.41

 offence

0.38

 offences

0.37

Activations Density 0.228%

references to criminal activity and serious offenses

No Comments

No Known Activations

references to criminal activity and serious offenses

No Comments

No Known Activations