INDEX

Explanations

phrases that express skepticism or challenge common beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 however

-0.21

 However

-0.17

åį´

-0.16

 jedoch

-0.16

 HOWEVER

-0.15

åĪĻ

-0.15

Ø§ÙĥÙĨ

-0.15

 nevertheless

-0.15

smarty

-0.14

Ã©al

-0.14

POSITIVE LOGITS

0.16

 importantly

0.16

è¿Ľä¸ĢæŃ¥

0.15

 ná»¯a

0.15

 equally

0.14

odash

0.14

-Za

0.14

otto

0.14

Activations Density 0.325%

phrases that express skepticism or challenge common beliefs

No Comments

No Known Activations