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

-0.15

arro

-0.14

 Alternate

-0.14

æĿ¾

-0.13

è¦

-0.13

-stock

-0.13

elves

-0.13

’Ñı

-0.13

POSITIVE LOGITS

''

0.30

''

0.27

Ath

0.25

'''

0.24

Ath

0.23

 Oscars

0.21

'',

0.21

=''

0.21

:''

0.21

,''

0.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.