INDEX

Explanations

references to military experiences and actions in conflict zones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 wings

-0.15

 Wing

-0.15

 Wings

-0.15

 armed

-0.14

otr

-0.14

.Glide

-0.14

phia

-0.14

osate

-0.14

-0.13

KS

-0.13

POSITIVE LOGITS

 Afghan

0.26

 coalition

0.25

 Afghanistan

0.24

 Coalition

0.24

 Iraqi

0.24

 Taliban

0.23

 Iraq

0.23

Coal

0.22

IED

0.22

 roadside

0.21

Activations Density 0.081%

references to military experiences and actions in conflict zones

No Comments

No Known Activations