INDEX

Explanations

numerical data and references in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 VerfÃ¼gung

-0.16

UFF

-0.15

asket

-0.15

quals

-0.14

 Pipe

-0.14

 ÙħÙĩØ±

-0.13

alse

-0.13

Ð±Ð¸ÑĤ

-0.13

ìĦł

-0.13

apture

-0.13

POSITIVE LOGITS

 halinde

0.17

ysize

0.16

/pages

0.15

InputDialog

0.15

 pages

0.14

adora

0.14

adar

0.14

otron

0.14

 GLenum

0.14

arius

0.14

Activations Density 0.032%

numerical data and references in text

No Comments

No Known Activations