INDEX

Explanations

references to private entities or companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

_priv

-0.21

priv

-0.17

 priv

-0.17

tra

-0.17

 privat

-0.17

ssi

-0.17

ulp

-0.17

Privacy

-0.16

Priv

-0.16

PrivateKey

-0.16

POSITIVE LOGITS

-sector

0.39

 sector

0.35

/public

0.32

ering

0.30

-public

0.28

 Sector

0.28

Sector

0.25

/Public

0.24

-equ

0.23

-label

0.22

Activations Density 0.032%

references to private entities or companies

No Comments

No Known Activations