INDEX

Explanations

references to military ranks and roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 acomp

-0.14

Ø§Ø¨ÙĤ

-0.14

ÑĸÐ¹Ð½Ð¾

-0.13

ÙĦØŃ

-0.13

eni

-0.13

redo

-0.13

å»ºè¨Ń

-0.13

 evolution

-0.13

tail

-0.13

gn

-0.13

POSITIVE LOGITS

 arrived

0.27

 arrival

0.27

 debut

0.26

 arrive

0.25

 dÃ©but

0.25

 arrives

0.24

 entered

0.23

çĻ»åł´

0.23

 officially

0.23

 enters

0.22

Activations Density 0.082%

references to military ranks and roles

No Comments

No Known Activations