INDEX

Explanations

references to financial obligations and expenditures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Roy

-0.15

.Restrict

-0.14

Å¡ÃŃ

-0.14

 Gross

-0.14

 Sexo

-0.13

inoa

-0.13

 Indo

-0.13

 sÃłn

-0.13

 conduct

-0.13

adoo

-0.13

POSITIVE LOGITS

 responsibility

0.36

 responsible

0.30

 Responsibility

0.29

Respons

0.28

 Responsible

0.27

è´£ä»»

0.26

 footing

0.25

 respons

0.25

è²ł

0.25

 paying

0.25

Activations Density 0.233%

references to financial obligations and expenditures

No Comments

No Known Activations