INDEX

Explanations

database and programming-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

inha

-0.15

ÑīÐ°

-0.15

UnitOfWork

-0.15

allon

-0.14

ieber

-0.14

quat

-0.14

arov

-0.14

.opend

-0.14

adera

-0.14

atat

-0.13

POSITIVE LOGITS

Ã¥l

0.15

ÎºÎ¿

0.14

agent

0.14

atoi

0.14

bon

0.14

ë§Ĳ

0.13

alem

0.13

contre

0.13

 perfil

0.13

aggio

0.13

Activations Density 0.166%

database and programming-related terminology

No Comments

No Known Activations