INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

èĳĹ

-0.16

ighth

-0.15

inz

-0.15

uan

-0.14

idl

-0.14

cla

-0.13

 Ø§ÙĦÙħÙģ

-0.13

Ð¸Ð»ÑĮ

-0.13

inth

-0.13

inite

-0.13

POSITIVE LOGITS

0.15

fcn

0.15

 ABOVE

0.14

 Electoral

0.14

 Becker

0.14

AVA

0.14

 Archive

0.14

 archives

0.14

æ¡£

0.14

 Conserv

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.