INDEX

Explanations

references to Barack Obama and other U.S. political figures

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

ltk

-0.14

à¤¿à¤

-0.14

ÙĪØ§Ø±Ùĩ

-0.14

]={↵

-0.14

Ã¶yle

-0.14

yll

-0.14

åĲ§

-0.14

POSITIVE LOGITS

 Obama

0.25

 Trump

0.23

 Bush

0.22

Obama

0.20

 Biden

0.19

 Clinton

0.19

Trump

0.18

Bush

0.18

 Reagan

0.18

enus

0.16

Activations Density 0.024%

references to Barack Obama and other U.S. political figures

No Comments

No Known Activations