INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.WinForms

-0.15

 JpaRepository

-0.15

utzer

-0.15

ugu

-0.14

ÑģÑıÑĩ

-0.14

Å¡ak

-0.14

-dom

-0.14

isay

-0.14

ptal

-0.14

POSITIVE LOGITS

egl

0.17

 Fowler

0.14

 almost

0.14

anford

0.14

 Agility

0.13

 Company

0.13

 Clayton

0.13

 SPDX

0.13

 Gary

0.13

chter

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.