INDEX

Explanations

geographical and location-based information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ä¸ŃæĸĩåŃĹå¹ķ

-0.18

emoc

-0.17

 Unidos

-0.15

emos

-0.15

printStats

-0.15

acho

-0.15

 Ð¸Ð½Ð´Ð¸Ð²Ð¸Ð´Ñĥ

-0.14

èĦĤ

-0.14

 spokes

-0.13

-FIRST

-0.13

POSITIVE LOGITS

town

0.30

borough

0.27

villa

0.24

east

0.23

Town

0.23

west

0.23

roads

0.23

north

0.22

terrain

0.22

Terrain

0.22

Activations Density 0.253%

geographical and location-based information

No Comments

No Known Activations