INDEX

Explanations

mentions of technology and equipment-related terms

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

vÄĽd

-0.16

SWG

-0.16

aret

-0.15

-0.14

 Welch

-0.14

inn

-0.14

alto

-0.14

è¼ª

-0.14

æ´ĭ

-0.14

twitter

-0.14

POSITIVE LOGITS

 stabilization

0.23

DJ

0.22

gim

0.21

ollar

0.20

 stabilize

0.20

 stabil

0.18

 stabilized

0.18

udu

0.16

sj

0.16

mav

0.16

Activations Density 0.003%

mentions of technology and equipment-related terms

No Comments

No Known Activations