INDEX

Explanations

references to articles and discussions about writing and content creation

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

/files

-0.16

 Copies

-0.15

aira

-0.15

-0.14

Ð½Ð°Ñħ

-0.14

 textbooks

-0.14

ansk

-0.14

CDs

-0.13

 DVDs

-0.13

Ã¡y

-0.13

POSITIVE LOGITS

 article

0.76

article

0.58

-article

0.52

 Article

0.52

 post

0.50

 piece

0.47

 articles

0.47

Article

0.47

_article

0.46

 ARTICLE

0.46

Activations Density 0.627%

references to articles and discussions about writing and content creation

No Comments

No Known Activations