INDEX

Explanations

references to software licenses and usage restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

skou

-0.15

ander

-0.14

anges

-0.13

 saver

-0.13

orer

-0.13

quet

-0.13

 prompts

-0.13

 locker

-0.13

explode

-0.13

Ð°ÐºÑģÐ¸Ð¼

-0.13

POSITIVE LOGITS

ekl

0.18

ÑĸÐ»ÑĮ

0.14

è¯´çļĦ

0.14

OP

0.14

æĸĹ

0.14

processable

0.13

äºĭæ¥Ń

0.13

_equiv

0.13

Å¾iv

0.13

.getSeconds

0.13

Activations Density 0.113%

references to software licenses and usage restrictions

No Comments

No Known Activations