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

ars

-0.20

fro

-0.17

es

-0.17

owl

-0.15

 segments

-0.15

áº¡n

-0.15

iliary

-0.14

 Clifford

-0.14

Ag

-0.14

idi

-0.14

POSITIVE LOGITS

zcze

0.17

/REC

0.16

 Zaman

0.16

zt

0.15

 éĸ

0.15

mgr

0.14

ucas

0.14

specialchars

0.14

Mgr

0.14

ÎĿ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.