INDEX

Explanations

mentions of the name "Monte Carlo" or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ourke

-0.15

 Buccane

-0.15

eel

-0.15

aData

-0.15

peek

-0.15

indows

-0.14

/lg

-0.14

aded

-0.14

cxx

-0.14

oud

-0.14

POSITIVE LOGITS

 Carlo

0.35

clar

0.22

rosso

0.22

 Crist

0.21

ith

0.21

arlo

0.20

 Rosa

0.17

 Sinai

0.17

ITH

0.17

 Alban

0.17

Activations Density 0.006%

mentions of the name "Monte Carlo" or related terms

No Comments

No Known Activations