INDEX

Explanations

specific names of places and events

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

 towns

-0.22

 farm

-0.18

 Saskatchewan

-0.17

 Ø±ÙĪØ³Øª

-0.17

County

-0.15

çľĮ

-0.15

 kraje

-0.15

 REGION

-0.15

 Ontario

-0.15

NJ

-0.15

POSITIVE LOGITS

 city

0.32

 City

0.30

-city

0.29

 Metro

0.28

 CITY

0.26

City

0.26

 urban

0.26

city

0.26

 metro

0.26

 cityName

0.25

Activations Density 1.071%

specific names of places and events

No Comments

No Known Activations