INDEX

Explanations

terms related to machine learning and artificial intelligence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ITES

-0.18

 Thornton

-0.16

egin

-0.15

/misc

-0.15

Î¼Î¿Ïħ

-0.14

Ð´Ð°Ñı

-0.14

illos

-0.14

strup

-0.14

uben

-0.14

.Private

-0.14

POSITIVE LOGITS

 learning

0.26

-readable

0.26

-machine

0.23

 Learning

0.23

-learning

0.22

(machine

0.22

 readable

0.22

learning

0.21

gun

0.21

achine

0.20

Activations Density 0.007%

terms related to machine learning and artificial intelligence

No Comments

No Known Activations