INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Humph

-0.17

ext

-0.17

-0.16

tam

-0.15

 bubb

-0.14

unh

-0.14

isser

-0.14

 slow

-0.14

etu

-0.14

ujet

-0.14

POSITIVE LOGITS

ouz

0.18

 preferredStyle

0.17

ByUrl

0.16

\grid

0.15

ogui

0.14

 Pornhub

0.14

/slick

0.14

adro

0.14

Î©Î£

0.14

agma

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.