INDEX

Explanations

phrases related to software bugs and user interaction issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ãĥĭãĤ¢

-0.16

 queda

-0.15

upt

-0.15

-0.14

Pi

-0.14

la

-0.14

 Prospect

-0.14

tty

-0.14

ilet

-0.14

POSITIVE LOGITS

tem

0.35

Tem

0.30

Tem

0.29

_tem

0.27

TEM

0.27

TEM

0.24

tem

0.23

 Ã©

0.22

 Temple

0.20

 temples

0.20

Activations Density 0.017%

phrases related to software bugs and user interaction issues

No Comments

No Known Activations