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

Moo

-0.15

abox

-0.14

 Regardless

-0.14

eselect

-0.14

 å¯

-0.14

 marque

-0.14

akedirs

-0.13

Montserrat

-0.13

unlikely

-0.13

malar

-0.13

POSITIVE LOGITS

 Sharon

0.21

 (“

0.20

 occupation

0.19

 Occupation

0.18

 Israeli

0.18

ynet

0.18

occupation

0.18

IDF

0.17

 pione

0.17

 occup

0.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.