INDEX

Explanations

references to technology products and their features or developments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

yro

-0.15

ICT

-0.15

 motor

-0.14

ÏģÎ¿

-0.13

eldon

-0.13

iola

-0.13

 Writers

-0.13

.windows

-0.13

abbo

-0.13

hsv

-0.13

POSITIVE LOGITS

 Apple

0.30

 iPhone

0.29

 iPhones

0.25

Apple

0.25

.apple

0.24

 Face

0.23

iPhone

0.23

 apple

0.23

 Cupertino

0.22

 âĢĮ

0.22

Activations Density 0.008%

references to technology products and their features or developments

No Comments

No Known Activations