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

ologne

-0.15

 herk

-0.14

enstein

-0.14

ncia

-0.13

ncy

-0.13

ancode

-0.13

éº

-0.13

neau

-0.13

etta

-0.13

inium

-0.13

POSITIVE LOGITS

 Utility

0.32

Utility

0.28

/utility

0.26

 utility

0.26

UTILITY

0.23

utility

0.23

 Utilities

0.23

 utilities

0.19

Rip

0.19

 customer

0.19

Activations Density 0.000%

No Known Activations

This feature has no known activations.