INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

zen

-0.17

zend

-0.17

quiv

-0.14

 Tone

-0.14

zer

-0.14

 dart

-0.14

rement

-0.13

 connexion

-0.13

 fancy

-0.13

POSITIVE LOGITS

SystemService

0.15

à¸²à¸Ī

0.15

 Kindle

0.15

emonic

0.14

jur

0.14

Ð¼Ð¾Ñģ

0.14

 TMPro

0.14

utenberg

0.14

ardon

0.13

orsch

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.