INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

å¤«

-0.14

 Pride

-0.14

 Bund

-0.14

ÄĽji

-0.14

zeich

-0.14

/provider

-0.14

inecraft

-0.14

 pride

-0.13

eva

-0.13

reek

-0.13

POSITIVE LOGITS

 helmet

0.35

 Bell

0.33

 Helmet

0.33

Bell

0.32

Helmet

0.31

 Bull

0.31

 helmets

0.31

 rider

0.29

 riders

0.28

 bull

0.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.