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

ilon

-0.15

ãĤīãģĦ

-0.15

sez

-0.15

BD

-0.15

Rog

-0.14

 Clifford

-0.14

 Broadcasting

-0.13

 Clark

-0.13

 Shel

-0.13

iek

-0.13

POSITIVE LOGITS

 Ryan

0.24

Ryan

0.22

ryan

0.21

 Alex

0.19

 Jared

0.19

 alex

0.18

alex

0.17

Cri

0.17

ehr

0.16

runtime

0.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.