INDEX

Explanations

attributes and details related to written works, particularly essays and their structural elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 ÐµÑīÑĳ

-0.17

 ÑģÐµÑĢÑĮ

-0.15

 dÃ©cor

-0.15

 svÄĽ

-0.15

Ã¼b

-0.14

ÎŃÎ½

-0.14

ĽĪ

-0.13

 dafÃ¼r

-0.13

fÃ¼

-0.13

infra

-0.13

POSITIVE LOGITS

 descriptive

0.24

 write

0.21

 essay

0.21

 essays

0.20

.↵

0.20

essay

0.20

 persuasive

0.20

 dissertation

0.19

 argument

0.19

 favourite

0.19

Activations Density 0.008%

attributes and details related to written works, particularly essays and their structural elements

No Comments

No Known Activations