INDEX

Explanations

references to legal rulings and judicial proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

uchs

-0.17

 appellate

-0.16

ÙĨØ¬

-0.15

 nÄĽho

-0.14

ÑĨÐµÐ²

-0.13

 âĹĦ

-0.13

 Ð¿ÑĢÐ¸Ð²ÐµÐ´

-0.13

éŃ

-0.13

.shop

-0.13

 nghá»ĩ

-0.13

POSITIVE LOGITS

 pres

0.22

 order

0.21

 ruling

0.20

Order

0.18

order

0.18

ORDER

0.18

 judge

0.18

 orders

0.18

 Orders

0.18

 Order

0.18

Activations Density 0.114%

references to legal rulings and judicial proceedings

No Comments

No Known Activations