INDEX

Explanations

discussions about punctuation, specifically the usage of commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

çª

-0.16

-prefix

-0.15

argout

-0.15

 Ð¿ÐµÑĢÐµÐº

-0.15

ucas

-0.14

aliz

-0.14

å´İ

-0.14

Å¡tÄĽ

-0.14

 Jacob

-0.14

POSITIVE LOGITS

 punct

0.19

 punctuation

0.19

punkt

0.16

eshire

0.16

 trailing

0.15

 pause

0.15

jun

0.15

end

0.15

unctuation

0.15

 endl

0.15

Activations Density 0.067%

discussions about punctuation, specifically the usage of commas

No Comments

No Known Activations

discussions about punctuation, specifically the usage of commas

No Comments

No Known Activations