INDEX

Explanations

references to personal upbringing and childhood experiences

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

",__

-0.14

iasm

-0.13

eturn

-0.13

agina

-0.13

ãĥĲãĥ¼

-0.13

.yang

-0.12

ypy

-0.12

å¤«

-0.12

owl

-0.12

POSITIVE LOGITS

 surrounded

0.27

 idol

0.23

 hearing

0.22

 raised

0.22

 exposed

0.21

 immersed

0.21

 amid

0.21

 poor

0.21

 amidst

0.21

 bilingual

0.20

Activations Density 0.037%

references to personal upbringing and childhood experiences

No Comments

No Known Activations