INDEX

Explanations

terms related to machine learning frameworks and their configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 theory

-0.15

Ãº

-0.14

essel

-0.14

Tel

-0.14

 batt

-0.14

 spoilers

-0.13

lÃ©

-0.13

SECRET

-0.13

POSITIVE LOGITS

lix

0.15

biz

0.15

plex

0.15

åłĤ

0.14

ìĸĳ

0.14

imeo

0.14

arrant

0.14

BuilderFactory

0.14

ieten

0.14

 YÃ¶netim

0.14

Activations Density 0.001%

terms related to machine learning frameworks and their configurations

No Comments

No Known Activations