INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uyen

-0.17

arl

-0.15

ervo

-0.14

iors

-0.14

 ÙĩÙħÛĮÙĨ

-0.14

åįĹçľģ

-0.14

ãĥ¼ãĤº

-0.14

aan

-0.14

 scale

-0.14

sdale

-0.13

POSITIVE LOGITS

æĨ

0.15

æ³¡

0.13

ogl

0.13

å¢

0.13

.Orientation

0.13

agon

0.13

Subset

0.13

ERCHANT

0.13

LogLevel

0.13

ĮĴ

0.12

Activations Density 0.007%

No Comments

No Known Activations