INDEX

Explanations

positive feedback and appreciation for creative works

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

utenberg

-0.18

apas

-0.14

ÏģÎ·

-0.13

fried

-0.13

adget

-0.13

inÃ§

-0.13

terdam

-0.12

eyh

-0.12

 Gingrich

-0.12

ABL

-0.12

POSITIVE LOGITS

 commission

0.33

 commissions

0.31

 Commission

0.29

Commission

0.27

commission

0.27

 commissioned

0.27

 commissioners

0.23

 shading

0.21

 commissioner

0.21

 sculpt

0.20

Activations Density 0.020%

positive feedback and appreciation for creative works

No Comments

No Known Activations