INDEX

Explanations

references to violent incidents and criminal activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

_iff

-0.15

lico

-0.14

aille

-0.14

ãģªãĤī

-0.14

spm

-0.13

poster

-0.13

 Till

-0.13

zos

-0.13

ÂĢ

-0.13

 artÄ±k

-0.13

POSITIVE LOGITS

 while

0.36

 during

0.35

 whilst

0.29

during

0.29

while

0.28

_while

0.27

 WHILE

0.27

 durante

0.25

 During

0.24

 While

0.23

Activations Density 0.186%

references to violent incidents and criminal activities

No Comments

No Known Activations