INDEX

Explanations

phrases indicating significant impacts or effects in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

plusplus

-0.15

%č↵

-0.14

urrect

-0.14

adÄ±k

-0.13

BX

-0.13

Ø«Ø§ÙĦ

-0.13

ÏģÎ±Î²

-0.13

è·Į

-0.13

.Uri

-0.13

ãĥ³ãĥĶ

-0.13

POSITIVE LOGITS

 significant

0.59

 major

0.47

significant

0.47

 signific

0.46

 substantial

0.45

 dramatic

0.42

 Significant

0.42

 serious

0.42

 considerable

0.40

 Ð·Ð½Ð°Ñĩ

0.37

Activations Density 0.445%

phrases indicating significant impacts or effects in various contexts

No Comments

No Known Activations