INDEX

Explanations

phrases related to commands and difficulty levels in gaming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

#End

-0.15

oras

-0.14

wart

-0.14

 punches

-0.14

 Trophy

-0.14

fleet

-0.14

 lá»Ŀi

-0.14

çĽŁ

-0.14

-urlencoded

-0.14

merchant

-0.13

POSITIVE LOGITS

CT

0.30

CT

0.25

 Dust

0.24

 Counter

0.23

bom

0.23

_CT

0.23

 bomb

0.22

.ct

0.22

CS

0.22

_ct

0.21

Activations Density 0.006%

phrases related to commands and difficulty levels in gaming

No Comments

No Known Activations