INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ling

-0.15

GRA

-0.14

 borderTop

-0.14

 sucker

-0.14

arent

-0.14

idUser

-0.14

ÐµÐ»ÐµÑĦ

-0.14

Region

-0.14

unders

-0.13

valuate

-0.13

POSITIVE LOGITS

 ones

0.16

Kr

0.15

VERRIDE

0.15

anic

0.14

ablish

0.14

okud

0.14

Ã¡li

0.13

berger

0.13

ellas

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.