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

 favors

-0.15

 harbor

-0.15

çĸ¾

-0.15

 unfavor

-0.15

 canceled

-0.14

odor

-0.14

ark

-0.14

 gray

-0.14

Ø¹Ùģ

-0.14

Neighbors

-0.13

POSITIVE LOGITS

Fun

0.32

fun

0.28

FUN

0.27

Fun

0.27

 Stage

0.25

_fun

0.22

fun

0.21

.fun

0.21

Stage

0.20

 Change

0.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.