INDEX

Explanations

references to privacy policies and related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.synthetic

-0.16

ulu

-0.14

iran

-0.14

hci

-0.14

ucu

-0.14

svc

-0.13

 Ders

-0.13

opro

-0.13

/LICENSE

-0.13

 Licensing

-0.13

POSITIVE LOGITS

 privacy

0.36

 Privacy

0.32

privacy

0.31

 personal

0.29

Privacy

0.28

 Personal

0.27

 collection

0.26

 handling

0.26

 storage

0.26

 processing

0.24

Activations Density 0.048%

references to privacy policies and related information

No Comments

No Known Activations