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

ctal

-0.14

Kot

-0.13

pok

-0.13

ROT

-0.13

ille

-0.13

agli

-0.13

ìļ©

-0.12

 multic

-0.12

Ð»Ð¸ÑĤ

-0.12

POSITIVE LOGITS

ABCDEFGHIJKLMNOP

0.15

apore

0.15

~-~-

0.14

 fucks

0.14

UrlParser

0.14

åħĭæĸ¯

0.14

æ¡Ī

0.14

ordum

0.13

shan

0.13

ubar

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.