INDEX

Explanations

references to historical figures and their contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

kill

-0.15

 kill

-0.15

åĨĬ

-0.14

/kernel

-0.14

å·ŀå¸Ĥ

-0.13

Ð°ÑĩÐµ

-0.13

 kingdom

-0.13

 prime

-0.13

dib

-0.13

 iron

-0.13

POSITIVE LOGITS

andan

0.16

tainment

0.16

@nate

0.15

ichert

0.14

ionage

0.14

PermissionsResult

0.14

 Hell

0.14

AndView

0.14

 erotische

0.14

#af

0.14

Activations Density 0.022%

references to historical figures and their contributions

No Comments

No Known Activations