INDEX

Explanations

terms related to magnets and their properties

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

èľľ

-0.19

iglia

-0.17

$rs

-0.16

èĭĹ

-0.16

åĥ

-0.15

veau

-0.15

.UIManager

-0.14

èĥŀ

-0.14

?>>

-0.14

ÙĬÙĦØ§Ø¯

-0.14

POSITIVE LOGITS

 magnetic

0.55

 magnet

0.54

 magnets

0.53

 Magnet

0.47

 Magnetic

0.47

ç£ģ

0.47

MAG

0.45

mag

0.45

 Ð¼Ð°Ð³

0.43

 Magn

0.42

Activations Density 0.038%

terms related to magnets and their properties

No Comments

No Known Activations