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

 rocking

-0.17

wner

-0.17

ories

-0.17

 rocked

-0.15

ials

-0.15

ropic

-0.14

ASI

-0.14

ê·¹

-0.14

reet

-0.14

amespace

-0.14

POSITIVE LOGITS

abil

0.38

ers

0.31

ument

0.27

steady

0.25

efeller

0.24

star

0.24

pile

0.24

aby

0.23

-solid

0.21

stars

0.21

Activations Density 0.010%

No Comments

No Known Activations