INDEX

Explanations

expressions of appreciation or acknowledgment in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

endale

-0.16

leneck

-0.16

 ZÃ¡p

-0.14

meg

-0.14

plevel

-0.14

ëª©

-0.14

ë¨¸

-0.13

Ð¾ÑģÑĤÐµÐ¹

-0.13

ground

-0.13

projection

-0.13

POSITIVE LOGITS

Rol

0.17

ëŀĮ

0.15

 Manning

0.15

Sav

0.15

Nug

0.15

Pou

0.15

 mane

0.14

contin

0.14

 Mane

0.14

aire

0.14

Activations Density 0.001%

expressions of appreciation or acknowledgment in communication

No Comments

No Known Activations