INDEX

Explanations

terminology related to disruptive behaviors in residential areas

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

ourg

-0.16

.transport

-0.15

 provid

-0.15

ouch

-0.15

æľºä¼ļ

-0.14

 transportation

-0.14

umo

-0.14

umbing

-0.14

enta

-0.13

 roky

-0.13

POSITIVE LOGITS

 neighbors

0.29

 noise

0.26

 neighbor

0.26

 Noise

0.26

 neighbours

0.25

Neighbors

0.25

neighbors

0.23

 neighbour

0.23

Noise

0.23

 Neighbor

0.22

Activations Density 0.103%

terminology related to disruptive behaviors in residential areas

No Comments

No Known Activations