INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

zza

-0.15

emann

-0.14

lp

-0.14

iyat

-0.14

urette

-0.14

 ifndef

-0.14

\grid

-0.14

Vz

-0.14

izard

-0.14

qml

-0.14

POSITIVE LOGITS

 å¤©

0.15

 Patreon

0.15

tej

0.15

Jac

0.14

anten

0.14

valuate

0.14

oplevel

0.14

Ð¡Ðł

0.14

ibir

0.14

antal

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.