INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 craw

-0.15

aub

-0.15

banks

-0.15

wand

-0.14

 seafood

-0.14

odom

-0.14

 Elder

-0.13

cdr

-0.13

 dumpster

-0.13

 kred

-0.13

POSITIVE LOGITS

 horse

0.54

 horses

0.52

 Horse

0.49

horse

0.46

 riders

0.39

 rider

0.38

 pony

0.36

 riding

0.35

 polo

0.35

 Riders

0.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.