INDEX

Explanations

textual elements related to specific numeric or detailed classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Ð²Ð¸ÑıÐ²

-0.31

 ÐµÑģÑĤÐµ

-0.25

 Ð¾Ð³ÑĢÐ°

-0.25

 Ð·Ð°ÑıÐ²

-0.24

 Ð·Ð²Ð¸ÑĩÐ°Ð¹

-0.21

 ÑĢÐ°Ð½ÑĮ

-0.20

 Ð¸Ð¼Ñĥ

-0.18

 Ð½ÐµÐ´ÐµÐ»

-0.18

 Ð²Ð¸ÑıÐ²Ð¸

-0.17

 Ð¿Ð¾Ð±Ð°

-0.16

POSITIVE LOGITS

 ÑģÐºÐ»Ð°Ð´Ð°

0.17

ãģ¡ãģ¯

0.17

çĶº

0.16

zab

0.15

yk

0.15

 Thá»±c

0.14

oeff

0.14

aeda

0.14

otron

0.14

illac

0.14

Activations Density 0.009%

textual elements related to specific numeric or detailed classifications

No Comments

No Known Activations