INDEX

Explanations

references to the name "Nelson," particularly associated with notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ewise

-0.16

ordum

-0.16

addon

-0.15

 Reform

-0.15

ovenant

-0.15

arp

-0.15

dej

-0.15

phyl

-0.15

ervlet

-0.14

IME

-0.14

POSITIVE LOGITS

 Mandela

0.38

 mand

0.26

 Mand

0.23

mand

0.21

 Nelson

0.21

Rol

0.20

 Rockefeller

0.17

 mandates

0.17

 roli

0.16

MAND

0.16

Activations Density 0.010%

references to the name "Nelson," particularly associated with notable figures

No Comments

No Known Activations