INDEX

Explanations

technical or programming terminology and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Ð¾Ð±ÐµÑģÐ¿Ðµ

-0.16

ëį°ìĿ´íĬ¸

-0.15

Ð½Ð°Ð´Ð»ÐµÐ¶

-0.15

usat

-0.15

ÑĢÐ¾Ð½Ð¸ÑĩÐµÑģ

-0.15

 Ð¸Ð½Ð´Ð¸Ð²Ð¸Ð´Ñĥ

-0.15

ï¼ĮåŃĺäºİ

-0.15

eÃ§

-0.14

 furthermore

-0.13

.Disclaimer

-0.13

POSITIVE LOGITS

 Ð¼Ð½Ðµ

0.24

 Ð¼Ð¾Ð³Ñĥ

0.23

 ÑħÐ¾ÑĩÑĥ

0.22

 Ð½Ð°Ð´Ð¾

0.22

 Ð¼Ð¾Ð¶ÐµÑĤÐµ

0.21

 ÐºÐ¾Ð½ÐµÑĩÐ½Ð¾

0.20

 Ð±ÑĥÐ´Ñĥ

0.20

 ÑħÐ¾ÑĤÐµÐ»

0.20

 ÑĤÑĥÑĤ

0.20

 Ð¿ÑĢÐ¸Ð´ÐµÑĤÑģÑı

0.20

Activations Density 0.062%

technical or programming terminology and structures

No Comments

No Known Activations