INDEX

Explanations

proper nouns related to individuals and government officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Victorian

-0.19

ï¼Īå¹³æĪĲ

-0.19

-0.17

Û±Û¹Û¹

-0.16

-0.15

Û²Û°Û±

-0.15

utherford

-0.15

elems

-0.15

 Nano

-0.14

POSITIVE LOGITS

0.54

0.45

0.39

ï¼ĪæĺŃåĴĮ

0.32

Û±Û¹Û¶

0.30

 USSR

0.29

0.27

 Soviet

0.26

Û±Û¹Ûµ

0.23

 Ð¡Ð¡Ð¡Ðł

0.23

Activations Density 1.390%

proper nouns related to individuals and government officials

No Comments

No Known Activations