INDEX

Explanations

references to system calls and code elements in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

illy

-0.18

ntl

-0.14

zzo

-0.14

att

-0.14

Îŀ

-0.13

 Atlas

-0.13

xm

-0.13

ÐµÐ»Ñİ

-0.13

 trung

-0.13

away

-0.13

POSITIVE LOGITS

uct

0.16

endregion

0.16

cl

0.15

ocker

0.15

etadata

0.14

},{↵

0.14

 Hast

0.13

Ð¼ÐµÐ½Ð°

0.13

getOrElse

0.13

 Dise

0.13

Activations Density 0.008%

references to system calls and code elements in programming

No Comments

No Known Activations