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

PIX

-0.17

-dialog

-0.16

HTTPS

-0.15

ãĤĨ

-0.15

 dialogs

-0.14

PKG

-0.14

adelphia

-0.14

DAO

-0.14

dialog

-0.14

 diff

-0.14

POSITIVE LOGITS

 publication

0.23

publication

0.22

 Publication

0.21

Publication

0.21

 Publications

0.20

 publications

0.19

 channel

0.19

 driver

0.19

 subscription

0.18

 Driver

0.18

Activations Density 0.000%

No Known Activations

This feature has no known activations.