INDEX

Explanations

terms related to trade secrets and legal protection

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Unsafe

-0.18

ignum

-0.16

psc

-0.16

ÑĩÐ°ÑĤ

-0.16

erif

-0.15

á»ħ

-0.15

unsafe

-0.15

igner

-0.15

adiens

-0.14

nett

-0.14

POSITIVE LOGITS

ND

0.24

 employee

0.24

 trade

0.23

 Trade

0.22

 Employee

0.22

 employees

0.21

nda

0.20

 competitor

0.20

 agreements

0.20

 competition

0.20

Activations Density 0.048%

terms related to trade secrets and legal protection

No Comments

No Known Activations