INDEX

Explanations

terms related to territorial and geopolitical issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

opr

-0.15

ecta

-0.14

ìĪĻ

-0.13

ÌĨ

-0.13

askell

-0.13

Ø§Ø¸

-0.13

Dock

-0.13

ossip

-0.13

acades

-0.13

 Ð¾Ð¿ÐµÑĢÐ°

-0.12

POSITIVE LOGITS

 territories

0.28

 territory

0.28

 Areas

0.27

 Jude

0.26

 areas

0.25

 West

0.24

 Jordan

0.24

 disputed

0.24

 annex

0.24

 Area

0.23

Activations Density 0.032%

terms related to territorial and geopolitical issues

No Comments

No Known Activations