INDEX

Explanations

references to political structures and government forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

fak

-0.18

iola

-0.14

SEN

-0.14

ampo

-0.14

pez

-0.14

Ø³ÙĨ

-0.13

rios

-0.13

 ØŃÙĤÙĪÙĤ

-0.13

eka

-0.13

oti

-0.13

POSITIVE LOGITS

 government

0.88

government

0.73

 Government

0.69

æĶ¿åºľ

0.68

Government

0.62

 governments

0.60

-government

0.59

 governo

0.57

 gobierno

0.54

 à¤¸à¤°à¤ķ

0.52

Activations Density 0.294%

references to political structures and government forms

No Comments

No Known Activations