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

æ±Ĺ

-0.15

fty

-0.15

ilot

-0.14

 kurs

-0.14

Ã¼h

-0.14

Credentials

-0.14

CI

-0.13

ÄħÅ¼

-0.13

Ã¶g

-0.13

 isot

-0.13

POSITIVE LOGITS

 Christmas

0.49

Christmas

0.44

 holiday

0.41

 christmas

0.40

 Santa

0.37

 Holiday

0.36

 Merry

0.35

Holiday

0.34

holiday

0.33

 holidays

0.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.