INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

æ§ĺ

-0.15

yre

-0.14

á»ĩ

-0.14

 ÙĩÙħÚĨÙĨÛĮÙĨ

-0.14

Decre

-0.14

oya

-0.14

ongan

-0.14

ãĤ

-0.14

ungan

-0.14

 impro

-0.13

POSITIVE LOGITS

finity

0.15

Ð»Ð°Ð½Ð´

0.15

 tvar

0.14

alue

0.14

 invent

0.14

rana

0.14

estro

0.13

çĲ³

0.13

 lParam

0.13

 Laden

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.