INDEX

Explanations

references to political leaders and government positions

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

nodoc

-0.18

Ã¼rger

-0.17

iston

-0.16

urbed

-0.15

Ã®t

-0.15

insky

-0.15

PLUGIN

-0.15

ÄįnÃ©

-0.15

CHA

-0.15

abbo

-0.14

POSITIVE LOGITS

 cabinet

0.40

 Cabinet

0.39

 Cabinets

0.37

 cabinets

0.34

 coalition

0.29

 ministers

0.28

 ministries

0.28

 Prime

0.27

 formation

0.27

 government

0.26

Activations Density 0.121%

references to political leaders and government positions

No Comments

No Known Activations