INDEX

Explanations

references to advertising and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Advertising

-0.18

 advertise

-0.18

 advertisements

-0.17

 advertiser

-0.17

 advertised

-0.17

 Advertising

-0.17

 advertisement

-0.16

Advertisements

-0.15

 advertisers

-0.15

nowledge

-0.15

POSITIVE LOGITS

 campaigns

0.25

hoc

0.24

verting

0.24

/mark

0.23

 campaign

0.22

/prom

0.21

-supported

0.21

orial

0.21

elaide

0.21

 placement

0.20

Activations Density 0.025%

references to advertising and related concepts

No Comments

No Known Activations