INDEX

Explanations

comparisons and similarities between various subjects or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

è¿Ļä¹Ī

-0.16

 ÄĳÃ¢y

-0.15

essa

-0.14

esktop

-0.14

orem

-0.14

them

-0.14

 nÃły

-0.13

ifferent

-0.13

these

-0.13

POSITIVE LOGITS

 those

0.42

 ones

0.40

 ours

0.37

those

0.35

 quello

0.35

 theirs

0.34

 what

0.33

 celui

0.32

 yours

0.28

 celle

0.27

Activations Density 0.291%

comparisons and similarities between various subjects or entities

No Comments

No Known Activations