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

xcf

-0.15

ãģĹãĤĥ

-0.15

uttle

-0.15

ymm

-0.15

SCRI

-0.15

Ã§ois

-0.14

mÃ¡

-0.14

hoff

-0.14

pollo

-0.14

emean

-0.14

POSITIVE LOGITS

TV

0.33

TV

0.31

tv

0.29

Tv

0.27

tv

0.27

_tv

0.27

 Ontario

0.26

Ont

0.26

Tv

0.26

 Ministry

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.