INDEX

Explanations

references to specific car models and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ote

-0.14

artner

-0.14

 paren

-0.14

 Airbnb

-0.14

STEM

-0.14

 Moore

-0.13

aso

-0.13

 Lenovo

-0.13

etty

-0.13

 Oswald

-0.13

POSITIVE LOGITS

 model

0.29

 models

0.26

model

0.24

-model

0.23

models

0.23

fac

0.21

 production

0.21

 modelo

0.21

 Ð¼Ð¾Ð´ÐµÐ»ÑĮ

0.21

 modÃ¨le

0.21

Activations Density 0.044%

references to specific car models and their characteristics

No Comments

No Known Activations