INDEX

Explanations

elements related to metadata in a document or image file

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ØªØ±ÛĮ

-0.15

ryan

-0.15

.Restr

-0.14

@show

-0.14

èĢħçļĦ

-0.14

RG

-0.14

rine

-0.14

bourne

-0.13

imer

-0.13

)test

-0.13

POSITIVE LOGITS

 rating

0.16

 ÎłÎ¬

0.15

izzo

0.15

isque

0.15

inspace

0.15

/MPL

0.15

edImage

0.14

Shot

0.14

 rated

0.14

Activations Density 0.003%

elements related to metadata in a document or image file

No Comments

No Known Activations