INDEX

Explanations

references to historical figures and royalty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

/apt

-0.15

 Stud

-0.15

 ìĶ¨

-0.15

spi

-0.14

Vys

-0.14

sam

-0.14

NSK

-0.14

kontakte

-0.14

ominated

-0.14

POSITIVE LOGITS

 Charles

0.25

 Victoria

0.22

 Frederick

0.20

 Ferdinand

0.19

 Edward

0.19

 Baldwin

0.19

ä¹¾

0.18

 George

0.18

 Louis

0.18

Charles

0.18

Activations Density 0.081%

references to historical figures and royalty

No Comments

No Known Activations