INDEX

Explanations

references to specific comic strips or cartoons

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

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

à¸²à¸ļ

-0.18

Emitter

-0.15

enko

-0.14

 cinemat

-0.14

lei

-0.14

--+

-0.14

.doc

-0.14

ijke

-0.13

<AudioSource

-0.13

DNA

-0.13

POSITIVE LOGITS

cart

0.39

 cartoon

0.38

-cart

0.38

 strip

0.37

 Cart

0.37

 cartoons

0.37

 strips

0.36

 synd

0.36

 cart

0.35

Cart

0.34

Activations Density 0.041%

references to specific comic strips or cartoons

No Comments

No Known Activations