INDEX

Explanations

phrases indicating purposes or functions associated with various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ties

-0.17

adele

-0.16

ilm

-0.15

mh

-0.15

ka

-0.15

usercontent

-0.15

mite

-0.15

andard

-0.14

alia

-0.14

mia

-0.14

POSITIVE LOGITS

 sake

0.29

geries

0.29

-profit

0.28

bidden

0.27

 purposes

0.24

 instance

0.24

aging

0.23

feit

0.23

/by

0.23

wards

0.20

Activations Density 0.722%

phrases indicating purposes or functions associated with various subjects

No Comments

No Known Activations