INDEX

Explanations

themes related to international relations and power dynamics

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

 backgrounds

-0.16

 Careers

-0.15

.UIManager

-0.15

å¾®è½¯éĽħé»ĳ

-0.15

 Career

-0.14

essel

-0.14

,:,

-0.13

ç§ģãģ®

-0.13

 Toll

-0.13

 sexually

-0.13

POSITIVE LOGITS

 military

0.22

 position

0.21

 economy

0.20

 domestic

0.20

 citizens

0.19

 nationals

0.19

 presence

0.18

 sovereignty

0.18

 borders

0.18

 navy

0.17

Activations Density 0.129%

themes related to international relations and power dynamics

No Comments

No Known Activations