INDEX

Explanations

phrases related to personally identifiable information and its classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

acers

-0.17

ateur

-0.16

ikal

-0.15

-0.14

ãĥ

-0.14

anco

-0.14

 Rodgers

-0.14

istrovstvÃŃ

-0.14

ozilla

-0.14

POSITIVE LOGITS

ulle

0.15

à¸§à¸Ķ

0.15

Ð¾Ð»Ð¾

0.15

.scalablytyped

0.14

Ø´Ùģ

0.14

endid

0.13

å¦

0.13

Emb

0.13

ouro

0.13

abolic

0.13

Activations Density 0.014%

phrases related to personally identifiable information and its classification

No Comments

No Known Activations