INDEX

Explanations

references to nations and their respective interests, especially in contexts involving policies and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

erator

-0.15

 ÐłÐ¾ÑģÑģÐ¸Ð¸

-0.15

 Pakistan

-0.14

 ÑĥÐºÑĢÐ°ÑĹÐ½ÑģÑĮÐºÐ¾ÑĹ

-0.14

 Careers

-0.14

essel

-0.14

 Nepal

-0.14

 Britain

-0.14

 Pennsylvania

-0.14

 careers

-0.13

POSITIVE LOGITS

 economy

0.30

 nationals

0.24

 citizens

0.23

 borders

0.23

 Gross

0.20

conomy

0.20

 position

0.19

 Constitution

0.19

 Economy

0.19

 currency

0.18

Activations Density 0.129%

references to nations and their respective interests, especially in contexts involving policies and relationships

No Comments

No Known Activations