INDEX

Explanations

technical terms and concepts related to quantum mechanics and diffusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

avern

-0.18

 Äĳ

-0.17

ooke

-0.15

mares

-0.14

itone

-0.14

.isBlank

-0.14

lim

-0.14

çķ«

-0.14

}elseif

-0.14

atron

-0.14

POSITIVE LOGITS

top

0.23

 protected

0.22

 Chern

0.22

 Hall

0.21

 Major

0.21

Dir

0.21

gap

0.20

protected

0.19

Top

0.19

 Protected

0.19

Activations Density 0.009%

technical terms and concepts related to quantum mechanics and diffusion

No Comments

No Known Activations