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

oya

-0.16

 Ãºn

-0.16

addock

-0.14

ungi

-0.14

 frog

-0.14

uga

-0.14

 èª

-0.14

ilename

-0.14

dirs

-0.13

POSITIVE LOGITS

 Denver

0.44

 Colorado

0.44

Denver

0.38

Colorado

0.36

 Boulder

0.34

 Rocky

0.28

 Rockies

0.28

 Jeff

0.28

 Colo

0.27

 Colum

0.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.