INDEX

Explanations

terms related to legal obligations and requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

venir

-0.16

agen

-0.16

utas

-0.14

arth

-0.14

Å¡k

-0.14

à¤°à¤£

-0.14

ouv

-0.14

æĸ¹éĿ¢

-0.14

assi

-0.14

OME

-0.14

POSITIVE LOGITS

by

0.25

ly

0.25

 under

0.23

/request

0.22

/lic

0.21

/generated

0.20

/not

0.20

ness

0.18

 into

0.17

ted

0.17

Activations Density 0.061%

terms related to legal obligations and requirements

No Comments

No Known Activations