INDEX

Explanations

programming-related terms, specifically those associated with user management and data handling in code

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

antu

-0.18

aro

-0.14

 mand

-0.14

 independ

-0.14

URN

-0.14

ì¡±

-0.14

Ð¾ÑģÑĥÐ´

-0.14

tej

-0.14

%^

-0.14

_inverse

-0.13

POSITIVE LOGITS

apore

0.15

ATUS

0.15

 ÙĤÙĬ

0.14

 Rapids

0.13

atab

0.13

RYPT

0.13

=&

0.13

ÄĽtÅ¡

0.13

à¸ĵ

0.13

isers

0.13

Activations Density 0.004%

programming-related terms, specifically those associated with user management and data handling in code

No Comments

No Known Activations