INDEX

Explanations

code-related syntax elements, particularly focusing on function declarations and calls

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

stÃŃ

-0.17

Ã¤Ã¤n

-0.16

_globals

-0.14

 Merk

-0.14

YPE

-0.14

è³¢

-0.14

zcze

-0.14

SPATH

-0.14

.ua

-0.13

eks

-0.13

POSITIVE LOGITS

cof

0.16

//

0.16

ÐºÑĥÐ»

0.15

xima

0.14

 rein

0.14

anz

0.14

inq

0.14

ullo

0.14

ount

0.14

èĭ

0.14

Activations Density 0.019%

code-related syntax elements, particularly focusing on function declarations and calls

No Comments

No Known Activations