INDEX

Explanations

terms related to confidentiality and legal obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ayo

-0.13

 neglected

-0.13

kt

-0.13

issan

-0.13

á»ħ

-0.13

 Moff

-0.13

.xz

-0.13

ä¸ģ

-0.13

erland

-0.13

POSITIVE LOGITS

 confidential

0.55

 confidentiality

0.51

 Confidential

0.49

 secrets

0.46

 secrecy

0.45

 privacy

0.44

 secret

0.43

 anonymity

0.38

 private

0.37

 Privacy

0.37

Activations Density 0.294%

terms related to confidentiality and legal obligations

No Comments

No Known Activations