INDEX

Explanations

technical terms and references related to web and application development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

cÃ©

-0.15

INDER

-0.14

eczy

-0.14

ear

-0.14

arra

-0.14

alled

-0.14

æŀ¶

-0.13

 gent

-0.13

lak

-0.13

POSITIVE LOGITS

-equiv

0.20

 "-//

0.16

 pragma

0.16

CLU

0.15

LES

0.15

odate

0.15

ë°Ģ

0.14

à¸ģà¸£à¸°

0.14

Î»Î¼

0.14

amburger

0.14

Activations Density 0.004%

technical terms and references related to web and application development

No Comments

No Known Activations