INDEX

Explanations

references to measurements or comparisons of different entities or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

woocommerce

-0.15

-0.14

unsch

-0.14

 unsus

-0.14

azon

-0.13

trag

-0.13

readonly

-0.13

à¹Ģà¸¥

-0.13

Ãµi

-0.12

 SUCCESS

-0.12

POSITIVE LOGITS

 considerable

0.40

 great

0.37

 strong

0.37

 extensive

0.37

 lots

0.36

 wide

0.36

 plenty

0.36

 tremendous

0.32

 frequent

0.31

cop

0.30

Activations Density 0.103%

references to measurements or comparisons of different entities or conditions

No Comments

No Known Activations