INDEX

Explanations

references to legal actions and formal processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

anke

-0.16

arching

-0.16

est

-0.16

erable

-0.15

ader

-0.15

izable

-0.15

ardin

-0.15

ÑģÑı

-0.15

oxide

-0.14

oder

-0.14

POSITIVE LOGITS

uator

0.28

uar

0.27

uated

0.26

uate

0.23

uating

0.21

inic

0.20

uellement

0.18

uation

0.18

uary

0.18

UAL

0.18

Activations Density 0.035%

references to legal actions and formal processes

No Comments

No Known Activations