INDEX

Explanations

references to artificial intelligence and its various applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ansi

-0.17

åŃĺäºİ

-0.16

raith

-0.16

 Geld

-0.14

xic

-0.14

ãĥ«ãĥĪ

-0.14

Ð½Ð¾Ð¿

-0.14

orsi

-0.14

omit

-0.14

pha

-0.14

POSITIVE LOGITS

lesen

0.17

akes

0.17

ayed

0.16

akens

0.16

itten

0.15

0.14

wd

0.14

rozen

0.14

addock

0.14

Activations Density 0.009%

references to artificial intelligence and its various applications

No Comments

No Known Activations