INDEX

Explanations

references to conferences and professional events focused on learning and networking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Ã³s

-0.16

aso

-0.15

aÃ±

-0.15

ÑĢÐµÐ¶Ð´

-0.15

Ð»Ð¾Ðº

-0.15

 Belmont

-0.15

à¸«à¸§

-0.15

vay

-0.14

usta

-0.13

ISCO

-0.13

POSITIVE LOGITS

rowse

0.17

Browse

0.14

ackets

0.14

rÅ¾

0.14

odash

0.14

essen

0.13

ainter

0.13

jte

0.13

stag

0.13

aks

0.13

Activations Density 0.097%

references to conferences and professional events focused on learning and networking

No Comments

No Known Activations