INDEX

Explanations

references to advertisements and marketing practices

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

uibModal

-0.15

/proto

-0.15

ä¾Ľ

-0.14

entanyl

-0.14

yect

-0.14

etros

-0.14

Ã±ana

-0.14

Insn

-0.14

anager

-0.14

atile

-0.13

POSITIVE LOGITS

ads

0.31

ad

0.30

 campaigns

0.29

 campaign

0.28

 commercials

0.25

 Campaign

0.25

Campaign

0.23

campaign

0.23

#ad

0.22

Ads

0.22

Activations Density 0.178%

references to advertisements and marketing practices

No Comments

No Known Activations