INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ultz

-0.16

ylim

-0.16

auf

-0.15

Ã¶m

-0.15

shots

-0.15

RYPT

-0.15

Ð»ÐµÐ¼

-0.15

rij

-0.14

klass

-0.14

laus

-0.14

POSITIVE LOGITS

ice

0.30

itor

0.29

itors

0.28

usz

0.27

vier

0.26

uar

0.26

et

0.24

uario

0.23

eway

0.23

ITOR

0.23

Activations Density 0.011%

No Comments

No Known Activations