INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.14

 absent

-0.14

exion

-0.14

obl

-0.14

kami

-0.14

atha

-0.14

xima

-0.13

 Surge

-0.13

Ħ

-0.13

avra

-0.13

POSITIVE LOGITS

.kr

0.16

ulton

0.16

ãİ¡

0.16

ableView

0.15

Ð±Ð¸

0.14

llib

0.14

asio

0.14

ercul

0.14

ugo

0.14

 Ð·Ð°ÐºÑĥÐ¿

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.