INDEX

Explanations

instances of promotional phrases or calls to action in advertisements

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

ansa

-0.16

agh

-0.15

amic

-0.15

bou

-0.14

xdb

-0.14

ouve

-0.14

anne

-0.14

acam

-0.14

ans

-0.14

uction

-0.14

POSITIVE LOGITS

 story

0.34

story

0.32

Story

0.26

 Story

0.26

 STORY

0.25

-story

0.25

.story

0.23

æķħäºĭ

0.23

/story

0.23

 stories

0.22

Activations Density 0.005%

instances of promotional phrases or calls to action in advertisements

No Comments

No Known Activations