INDEX

Explanations

phrases related to processes and actions occurring in a sequence or development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

llx

-0.15

ovna

-0.14

idge

-0.14

ÑģÐ¸ÑĤ

-0.14

à¸´à¸ķ

-0.14

zin

-0.13

ter

-0.13

 Bass

-0.13

æĦı

-0.13

uely

-0.13

POSITIVE LOGITS

rez

0.15

adan

0.15

Ð¾ÐºÐµ

0.14

ÏħÎ½Î±

0.14

kovi

0.14

ãģ¹ãģį

0.14

adier

0.14

Rug

0.13

ÐµÑĢÐ¿

0.13

akan

0.13

Activations Density 0.131%

phrases related to processes and actions occurring in a sequence or development

No Comments

No Known Activations