INDEX

Explanations

references to online engagement and visibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 æ±

-0.15

Advertis

-0.14

dum

-0.14

phetamine

-0.14

uhn

-0.13

izarre

-0.13

Kum

-0.13

 forth

-0.13

Ð½Ð¾Ð·

-0.13

 Hardcover

-0.13

POSITIVE LOGITS

 online

0.46

online

0.38

-online

0.37

 Online

0.36

 Internet

0.36

Online

0.34

_online

0.34

 ONLINE

0.33

Internet

0.33

 internet

0.33

Activations Density 0.390%

references to online engagement and visibility

No Comments

No Known Activations