INDEX

Explanations

references to various museums and their exhibits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÑĪÐ¸Ð±

-0.15

asan

-0.14

isle

-0.14

å¸Ń

-0.14

alf

-0.14

Ã³l

-0.14

êµ´

-0.13

aldo

-0.13

graf

-0.13

Ã³

-0.13

POSITIVE LOGITS

ÚĨÙĩ

0.17

/gallery

0.15

 collections

0.15

KeyType

0.15

illos

0.15

.sourceforge

0.14

oft

0.14

collections

0.14

presso

0.14

 contents

0.14

Activations Density 0.064%

references to various museums and their exhibits

No Comments

No Known Activations