INDEX

Explanations

references to military capabilities and operations

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

emoc

-0.18

 Squadron

-0.15

 Armed

-0.15

kowski

-0.14

 Milit

-0.14

_flux

-0.14

 militar

-0.13

HZ

-0.13

Ð¸ÑĤÐµ

-0.13

arem

-0.13

POSITIVE LOGITS

 tank

0.33

 tanks

0.32

hel

0.30

 Tanks

0.29

 helicopter

0.28

 helicopters

0.27

hel

0.26

 helicopt

0.26

air

0.25

 ground

0.25

Activations Density 0.188%

references to military capabilities and operations

No Comments

No Known Activations