INDEX

Explanations

instances of government authority and the use of force

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

enemy

-0.16

/ws

-0.15

/rfc

-0.15

antiago

-0.14

 enemy

-0.14

lush

-0.14

Enemy

-0.14

defense

-0.14

hid

-0.14

.decorate

-0.14

POSITIVE LOGITS

 force

0.38

 violence

0.33

 FORCE

0.32

force

0.31

 Force

0.31

-force

0.29

 resort

0.29

 Violence

0.28

 physical

0.27

Force

0.27

Activations Density 0.199%

instances of government authority and the use of force

No Comments

No Known Activations