INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

duck

-0.15

etur

-0.14

creds

-0.14

 threw

-0.13

 fidelity

-0.13

pii

-0.13

 Cord

-0.13

ffi

-0.13

apolis

-0.13

 mocking

-0.13

POSITIVE LOGITS

 license

0.24

 License

0.22

-License

0.22

-license

0.21

 licenses

0.20

 licence

0.20

 licensing

0.20

 Licence

0.20

 licensee

0.19

 LICENSE

0.19

Activations Density 0.000%

No Known Activations

This feature has no known activations.