INDEX

Explanations

occurrences of the term "machine" and its variations, indicating a focus on machine learning technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ÐµÐ»Ñİ

-0.15

strup

-0.15

ITES

-0.15

ric

-0.15

ÑĸÐ´Ð½Ð¾

-0.15

ÑģÐºÐ»Ð°Ð´

-0.14

ackbar

-0.14

egin

-0.14

Î¼Î¿Ïħ

-0.14

illos

-0.14

POSITIVE LOGITS

-readable

0.27

-machine

0.24

 learning

0.23

(machine

0.22

.machine

0.22

 readable

0.21

 Machine

0.21

 machine

0.20

 Learning

0.20

-learning

0.19

Activations Density 0.008%

occurrences of the term "machine" and its variations, indicating a focus on machine learning technologies

No Comments

No Known Activations