INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

esa

-0.15

alendar

-0.15

 ActionTypes

-0.14

ench

-0.14

.Unique

-0.14

ahl

-0.14

ìķ¼

-0.14

::$

-0.14

ROL

-0.14

POSITIVE LOGITS

 Hlav

0.15

 Autor

0.14

avana

0.14

arÃ¡

0.14

argas

0.14

ëĮ

0.14

æ¶ī

0.14

 chain

0.13

bad

0.13

 COMPUTER

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.