INDEX

Explanations

phrases that highlight the significance or importance of ideas or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ile

-0.15

ables

-0.15

aken

-0.15

Ã¡b

-0.14

@update

-0.14

ormsg

-0.14

Ø¬Ø§Ø±

-0.14

POSITIVE LOGITS

 importantly

0.54

 Import

0.37

Import

0.28

 important

0.28

 more

0.27

important

0.25

 worse

0.25

 import

0.24

 importante

0.23

 Important

0.23

Activations Density 0.176%

phrases that highlight the significance or importance of ideas or topics

No Comments

No Known Activations