INDEX

Explanations

references to extremist groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

apolis

-0.16

Ø±ÙĪØª

-0.14

sville

-0.14

alars

-0.13

inox

-0.13

occo

-0.13

ADX

-0.13

ÙĬÙĦØ§

-0.13

ecko

-0.13

(P

-0.13

POSITIVE LOGITS

-Qaeda

0.26

-'

0.23

-Q

0.22

aa

0.22

 Qaeda

0.22

-Z

0.21

-Jul

0.21

-N

0.21

-J

0.21

-Sh

0.21

Activations Density 0.017%

references to extremist groups

No Comments

No Known Activations