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

 thinner

-0.15

imler

-0.14

dbg

-0.14

 Turk

-0.14

istrat

-0.13

ì§ģ

-0.13

rak

-0.13

ØŃÙĦ

-0.13

.ImageLayout

-0.13

endsWith

-0.13

POSITIVE LOGITS

Tot

0.44

Tot

0.35

tot

0.31

AC

0.30

tot

0.29

_tot

0.26

 event

0.26

TOT

0.25

 Bass

0.24

 events

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.