INDEX

Explanations

topics related to legal issues and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

etch

-0.17

 Cultural

-0.15

chio

-0.14

ÑĢÐ¸Ð³

-0.14

Aqu

-0.14

rente

-0.14

omat

-0.14

Ø§ÙĨÙĪ

-0.14

rita

-0.14

iyel

-0.14

POSITIVE LOGITS

 FEMA

0.22

ERGE

0.19

 vide

0.18

vide

0.17

curities

0.16

 vidÃ©

0.16

elsey

0.15

 Goods

0.15

arge

0.15

 uniformly

0.15

Activations Density 0.013%

topics related to legal issues and frameworks

No Comments

No Known Activations