INDEX

Explanations

references to Star Trek characters and plots

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ighted

-0.15

 Caval

-0.14

à¸¥à¸Ńà¸ĩ

-0.14

Î´Î±

-0.14

éĴŁ

-0.14

ahat

-0.14

 Gast

-0.14

POSITIVE LOGITS

 Enterprise

0.39

 Kling

0.38

 Federation

0.37

Enterprise

0.35

 Star

0.34

 Vulcan

0.33

 Trek

0.33

 federation

0.30

Star

0.29

Vul

0.28

Activations Density 0.045%

references to Star Trek characters and plots

No Comments

No Known Activations