INDEX

Explanations

references to governmental and administrative entities and their functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

bero

-0.15

egrity

-0.15

uat

-0.15

Įĵ

-0.14

ÙĨØ§ÙħÙĩ

-0.14

 khÃ¡ng

-0.13

FLAGS

-0.13

TEE

-0.13

itz

-0.13

sir

-0.13

POSITIVE LOGITS

 Department

0.24

 Ministry

0.23

 authorities

0.22

 government

0.21

 Bureau

0.21

 agencies

0.21

 ministry

0.19

 Dept

0.19

 agency

0.19

Department

0.18

Activations Density 0.448%

references to governmental and administrative entities and their functions

No Comments

No Known Activations