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

opoulos

-0.15

quan

-0.14

pickup

-0.14

wicklung

-0.14

zhou

-0.14

isme

-0.14

 stash

-0.14

Guy

-0.14

qui

-0.13

eltas

-0.13

POSITIVE LOGITS

 Polish

0.35

Å

0.31

 Poland

0.29

 Warsaw

0.27

 polish

0.25

 Krak

0.25

Å

0.23

 Åļ

0.23

 Stan

0.23

Woj

0.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.