INDEX

Explanations

instances of the word "each."

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

 otherwise

-0.26

 else

-0.23

Otherwise

-0.21

 Otherwise

-0.20

Else

-0.20

 Else

-0.19

otherwise

-0.19

 ELSE

-0.18

Ð½Ð°ÑĩÐµ

-0.17

 everyone

-0.17

POSITIVE LOGITS

other

0.34

others

0.33

-other

0.30

 others

0.29

 Other

0.28

 other

0.28

 Others

0.28

 OTHER

0.28

Other

0.27

Others

0.26

Activations Density 0.017%

instances of the word "each."

No Comments

No Known Activations