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

DMI

-0.16

Ãºp

-0.15

utdown

-0.14

Ãºb

-0.14

 Fulton

-0.14

 Hizmet

-0.14

Ã¢u

-0.14

combe

-0.13

zÄħd

-0.13

Nonce

-0.13

POSITIVE LOGITS

Bel

0.27

Bos

0.26

 Bosnia

0.21

.rs

0.21

 Serbian

0.20

 Hand

0.20

Ban

0.20

Voj

0.19

 Kosovo

0.19

 Mont

0.19

Activations Density 0.000%

No Known Activations

This feature has no known activations.