INDEX

Explanations

references to awards, honors, and achievements in sports and literature

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

-0.16

ulet

-0.15

Ã«r

-0.15

ajas

-0.14

 meiden

-0.14

tÃ©

-0.14

auge

-0.14

LIC

-0.14

finger

-0.14

aper

-0.14

POSITIVE LOGITS

 numer

0.16

Î½Î±Î½

0.16

idos

0.14

roker

0.14

ë¡Ŀ

0.14

 æıĲ

0.14

antes

0.14

_batches

0.13

OTAL

0.13

 ling

0.13

Activations Density 0.064%

references to awards, honors, and achievements in sports and literature

No Comments

No Known Activations