INDEX

Explanations

references to concepts of "something" or its variations, suggesting an exploration or discussion of unidentified or abstract subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

uchen

-0.14

CLS

-0.14

hend

-0.14

Ð¸ÑģÑĤÑĢÐ°

-0.14

lsa

-0.14

FileSync

-0.14

ummer

-0.13

erer

-0.13

rze

-0.13

dden

-0.13

POSITIVE LOGITS

 contempor

0.15

gressive

0.15

kol

0.14

ello

0.14

ÑĶÐ¼

0.13

 Feder

0.13

 contemporary

0.13

retty

0.13

jin

0.13

ä¸įçŁ¥

0.13

Activations Density 0.031%

references to concepts of "something" or its variations, suggesting an exploration or discussion of unidentified or abstract subjects

No Comments

No Known Activations