INDEX

Explanations

references to advertising technology and implementation details

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

pdo

-0.13

leen

-0.13

lectron

-0.13

ä»ĺãģĳ

-0.13

-pills

-0.13

urgeon

-0.12

-git

-0.12

 Morph

-0.12

odata

-0.12

alphabet

-0.12

POSITIVE LOGITS

Ads

0.34

ads

0.33

Ads

0.32

Interstitial

0.31

 advertisers

0.29

 advertiser

0.29

Ad

0.28

 ê´ĳê³ł

0.28

 Advertising

0.27

.ads

0.27

Activations Density 0.020%

references to advertising technology and implementation details

No Comments

No Known Activations