INDEX

Explanations

words associated with actions or decisions made by characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

gow

-0.17

esub

-0.15

apter

-0.15

tick

-0.15

anvas

-0.14

 Ð¿Ð¾Ð´Ð°

-0.13

tÄ±r

-0.13

tit

-0.13

elve

-0.13

Naw

-0.13

POSITIVE LOGITS

 kÃ¶n

0.32

 dÃ¼r

0.29

 kÃ¶nnen

0.29

 kÃ¶nnte

0.27

 lassen

0.26

 wollen

0.24

 mÃ¶

0.23

 mÃ¼

0.23

 mÃ¶chten

0.23

 sollen

0.22

Activations Density 0.013%

words associated with actions or decisions made by characters

No Comments

No Known Activations