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

icode

-0.18

-0.17

utdown

-0.16

Ã¼lt

-0.15

ëŀį

-0.15

ulas

-0.15

 NÄĽkter

-0.15

afs

-0.14

 Southampton

-0.14

 Baghd

-0.14

POSITIVE LOGITS

 Czech

0.36

Jar

0.34

Jar

0.31

 Prague

0.28

.cz

0.26

Boh

0.25

jar

0.25

 PlzeÅĪ

0.25

 Brno

0.25

Him

0.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.