INDEX

Explanations

concepts related to holographic theories in physics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 PureComponent

-0.16

 sparing

-0.15

mey

-0.14

emer

-0.14

Zac

-0.14

igram

-0.14

 Perr

-0.14

åĭ¢

-0.13

.Selenium

-0.13

Roo

-0.13

POSITIVE LOGITS

 inflation

0.33

 infl

0.28

flation

0.27

 inflate

0.26

inflate

0.23

 rehe

0.22

 Prim

0.20

 prim

0.20

 Inflate

0.19

 inflated

0.19

Activations Density 0.008%

concepts related to holographic theories in physics

No Comments

No Known Activations