INDEX

Explanations

references to military and geopolitical cooperation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

opher

-0.15

 countryside

-0.15

ĵĺ

-0.15

arih

-0.14

IBC

-0.14

Ø´Ùĩ

-0.14

 downloadable

-0.14

Î»ÎµÎº

-0.14

oose

-0.14

rape

-0.13

POSITIVE LOGITS

 allies

0.25

 ally

0.25

 Washington

0.24

 friendly

0.22

 arch

0.21

Washington

0.19

 partners

0.19

 Moscow

0.19

 Ankara

0.19

 Turkey

0.18

Activations Density 0.213%

references to military and geopolitical cooperation

No Comments

No Known Activations