INDEX

Explanations

references to images and their sources or credits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 ActionTypes

-0.21

æħİ

-0.16

Ø¹ÙĨÙĪØ§ÙĨ

-0.15

ibold

-0.15

arrant

-0.15

-0.14

Ð±Ð¾Ð¼

-0.14

afs

-0.14

erson

-0.14

aires

-0.14

POSITIVE LOGITS

PA

0.29

PA

0.28

_PA

0.20

 PRESS

0.19

 Press

0.18

Mirror

0.18

stock

0.18

 Picture

0.17

Sup

0.17

 Mirror

0.17

Activations Density 0.012%

references to images and their sources or credits

No Comments

No Known Activations