INDEX

Explanations

concepts related to ongoing processes and continuous improvement

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

immutable

-0.16

iguiente

-0.14

ullet

-0.14

atform

-0.13

_catalog

-0.13

¶Į

-0.13

agoon

-0.13

ÐºÑĥÑģ

-0.13

_SPE

-0.13

Catalog

-0.13

POSITIVE LOGITS

elli

0.18

ASI

0.15

icit

0.15

ansa

0.14

Ð»ÑİÐ´

0.14

rait

0.14

 glBegin

0.14

@update

0.14

ãĤ¤ãĥĦ

0.14

Activations Density 0.231%

concepts related to ongoing processes and continuous improvement

No Known Activations