INDEX

Explanations

terms related to quantities and copies of items, particularly in the context of media and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

zdy

-0.15

 uÄŁ

-0.14

 Gust

-0.14

ameleon

-0.14

FIT

-0.13

togroup

-0.13

/dist

-0.13

arrass

-0.13

è»

-0.13

 Simulator

-0.13

POSITIVE LOGITS

of

0.40

 cá»§a

0.33

 thereof

0.24

 versions

0.22

 version

0.21

à¸Ĥà¸Ńà¸ĩ

0.20

/cop

0.20

of

0.19

 à¸Ĥà¸Ńà¸ĩ

0.18

à¸²à¸Ĥà¸Ńà¸ĩ

0.18

Activations Density 0.198%

terms related to quantities and copies of items, particularly in the context of media and products

No Comments

No Known Activations