INDEX

Explanations

references to government agencies and legal frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Economy

-0.15

å¿į

-0.15

DSA

-0.14

 smack

-0.14

CFG

-0.14

ãĥŃãĥ¼

-0.14

 Weld

-0.14

 ----------------------------------------------------------------------------↵

-0.14

 Enterprise

-0.13

Å¾

-0.13

POSITIVE LOGITS

 worldwide

0.37

 countries

0.31

 global

0.29

 Worldwide

0.28

global

0.27

åħ¨çĲĥ

0.25

 Countries

0.25

countries

0.24

 nations

0.23

Countries

0.23

Activations Density 0.340%

references to government agencies and legal frameworks

No Comments

No Known Activations