INDEX

Explanations

No Explanations Found

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

uzzi

-0.14

 Oakland

-0.14

 Perth

-0.14

SWG

-0.14

 Covenant

-0.14

 Karlov

-0.14

=”

-0.14

_:

-0.13

“

-0.13

ContentLoaded

-0.13

POSITIVE LOGITS

Nep

0.28

 Nepal

0.26

NE

0.20

 users

0.19

NE

0.19

 user

0.19

 traders

0.18

 Dash

0.17

user

0.17

 trading

0.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.