INDEX

Explanations

references to historical empires or monarchies

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

-0.17

oday

-0.15

ieder

-0.15

bum

-0.15

angu

-0.14

 guar

-0.14

 behaviors

-0.14

 cazzo

-0.14

arus

-0.14

ardin

-0.13

POSITIVE LOGITS

zoo

0.14

 é¦

0.13

Zoo

0.13

 Recent

0.13

ÐµÐ»ÐµÐ½

0.13

 Mitar

0.13

elsing

0.13

 å©

0.13

tr

0.13

DAQ

0.13

Activations Density 0.048%

references to historical empires or monarchies

No Comments

No Known Activations