INDEX

Explanations

hyperlinks or references to additional information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

istrovstvÃŃ

-0.15

è¡Ĩ

-0.14

fÃ¼g

-0.14

UsageId

-0.14

yonel

-0.14

ompiler

-0.14

ANCEL

-0.14

jejer

-0.14

íĸ¥

-0.14

iez

-0.13

POSITIVE LOGITS

 news

0.32

 News

0.27

 blog

0.27

 gallery

0.25

 Blog

0.25

news

0.25

News

0.24

 About

0.23

 contact

0.23

blog

0.22

Activations Density 0.232%

hyperlinks or references to additional information

No Comments

No Known Activations