INDEX

Explanations

references to airports and transportation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

isle

-0.17

artisan

-0.15

 eins

-0.15

sek

-0.15

 Seas

-0.14

boo

-0.14

uld

-0.14

 admit

-0.13

odie

-0.13

sein

-0.13

POSITIVE LOGITS

 airport

0.56

 Airport

0.50

 airports

0.50

airport

0.47

æľºåľº

0.43

Airport

0.42

 runway

0.35

 terminal

0.35

 Terminal

0.35

 ÙģØ±ÙĪØ¯Ú¯Ø§Ùĩ

0.33

Activations Density 0.102%

references to airports and transportation

No Comments

No Known Activations