INDEX

Explanations

references to historical interviews and discussions about political topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Nano

-0.16

ateral

-0.16

 Nano

-0.16

 LGBT

-0.15

 Global

-0.15

 Sustainability

-0.15

å¤¢

-0.14

 âĤ¬

-0.14

ustain

-0.14

emetery

-0.14

POSITIVE LOGITS

0.27

0.24

0.23

 USSR

0.21

ï¼ĪæĺŃåĴĮ

0.19

 Decimal

0.19

 apartheid

0.19

 Thatcher

0.19

 Yugoslavia

0.18

icens

0.18

Activations Density 0.367%

references to historical interviews and discussions about political topics

No Comments

No Known Activations

references to historical interviews and discussions about political topics

No Comments

No Known Activations