INDEX

Explanations

punctuations and symbols used to denote dialogue or emphasize points in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

/assert

-0.17

TION

-0.16

onte

-0.15

arez

-0.15

INVAL

-0.15

ection

-0.14

cene

-0.14

åħ¶ä¸Ń

-0.14

 Ulus

-0.14

POSITIVE LOGITS

 namely

0.29

 ë°Ķë¡ľ

0.22

nam

0.22

Nam

0.19

 totiÅ¾

0.19

Nam

0.17

 ones

0.16

viz

0.15

 ÄĲÃ³

0.15

 Ø§ÛĮÙĨÚ©Ùĩ

0.15

Activations Density 0.080%

punctuations and symbols used to denote dialogue or emphasize points in text

No Comments

No Known Activations