INDEX

Explanations

specific identifiers or terms related to organizations and entities

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

issen

-0.15

">ÃĹ</

-0.14

iá»ģn

-0.14

.lp

-0.14

Ã¶n

-0.14

-thumbnails

-0.13

à¤Ĥà¤¡à¤²

-0.13

ÑĢÐ°Ð²Ð°

-0.13

á»įng

-0.13

/mod

-0.13

POSITIVE LOGITS

 press

0.31

 Press

0.30

Press

0.28

press

0.27

 PRESS

0.26

PRESS

0.23

_press

0.22

 Credit

0.21

Credit

0.21

Submitted

0.21

Activations Density 0.017%

specific identifiers or terms related to organizations and entities

No Comments

No Known Activations