INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

/GPL

-0.16

etting

-0.15

ilog

-0.15

edl

-0.14

etten

-0.14

ternet

-0.14

ceae

-0.14

ì°®

-0.13

aterno

-0.13

rase

-0.13

POSITIVE LOGITS

ë¡

0.13

 bolt

0.13

ë¶Ģ

0.13

 Modern

0.13

 íĪ¬

0.13

Tee

0.13

utes

0.13

ãĥĸãĥŃ

0.13

 shower

0.13

ÌĢ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.