INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ahir

-0.17

Vin

-0.15

aban

-0.15

enberg

-0.14

 tens

-0.14

ael

-0.14

 embar

-0.14

fla

-0.14

 Bone

-0.14

-0.13

POSITIVE LOGITS

oger

0.16

alc

0.15

Ð¾ÑģÑĮ

0.14

igkeit

0.14

ä¼¼

0.14

etroit

0.14

orado

0.13

Ä±lÄ±Ã§

0.13

pecified

0.13

ĵåĲį

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.