INDEX

Explanations

references to the concept of being "behind the scenes" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 underlying

-0.18

unas

-0.17

ioc

-0.16

idan

-0.15

erif

-0.15

 Bylo

-0.14

æĬľ

-0.14

aya

-0.14

inox

-0.14

ombie

-0.14

POSITIVE LOGITS

 scenes

0.46

 Scenes

0.39

-scenes

0.37

scenes

0.35

 curtain

0.32

 closed

0.30

 veil

0.29

 curtains

0.26

 mask

0.25

closed

0.23

Activations Density 0.020%

references to the concept of being "behind the scenes" in various contexts

No Comments

No Known Activations