INDEX

Explanations

numerical data and specific dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

á¿Ĩ

-0.16

.scalablytyped

-0.16

Äģn

-0.15

ÄĻd

-0.14

ïľ

-0.14

Ú¯Ø§Ø¨

-0.14

ÃŃcÃŃ

-0.14

 íĮĮìĿ¼ì²¨ë¶Ģ

-0.14

á¹

-0.14

à¤¾à¤§à¤¨

-0.14

POSITIVE LOGITS

0.49

 fourth

0.39

 Fourth

0.37

 four

0.36

ï¼Ķ

0.32

Û´

0.32

-four

0.32

åĽĽ

0.31

 Four

0.31

 cuatro

0.31

Activations Density 0.079%

numerical data and specific dates

No Comments

No Known Activations