INDEX

Explanations

references to websites and online content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

amus

-0.20

elian

-0.17

ael

-0.14

Lorem

-0.13

zych

-0.13

.routes

-0.13

ensitive

-0.13

åĿĬ

-0.13

aporan

-0.13

uren

-0.13

POSITIVE LOGITS

 website

0.64

website

0.53

 Website

0.49

 websites

0.49

ç½ĳç«Ļ

0.46

Website

0.43

_website

0.41

 webpage

0.40

.website

0.37

 Ø§ÙĦÙħÙĪÙĤØ¹

0.36

Activations Density 0.323%

references to websites and online content

No Comments

No Known Activations