INDEX

Explanations

expressions of admiration or positive reactions to people or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-0.16

onth

-0.16

an

-0.15

rei

-0.15

ei

-0.15

oris

-0.14

kara

-0.14

ÑĢÐµÐº

-0.14

andalone

-0.14

cid

-0.14

POSITIVE LOGITS

by

0.23

ingly

0.20

 oleh

0.19

 bá»Łi

0.16

ooter

0.16

Î®

0.15

/dist

0.15

illance

0.15

ajar

0.15

contres

0.15

Activations Density 0.066%

expressions of admiration or positive reactions to people or situations

No Comments

No Known Activations

expressions of admiration or positive reactions to people or situations

No Comments

No Known Activations