INDEX

Explanations

documentation and comments within code indicating authorship and class information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

rega

-0.17

ente

-0.17

 Berger

-0.15

rent

-0.15

rese

-0.15

enti

-0.14

SCM

-0.14

oyo

-0.14

 entr

-0.13

POSITIVE LOGITS

copyright

0.17

 AUTHOR

0.17

 Author

0.17

 COPYRIGHT

0.16

ä½ľèĢħ

0.15

 author

0.15

stakes

0.15

Copyright

0.15

 PureComponent

0.15

uteur

0.15

Activations Density 0.011%

documentation and comments within code indicating authorship and class information

No Comments

No Known Activations