INDEX

Explanations

references to legislation and regulatory measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 federal

-0.18

 Federal

-0.16

acha

-0.14

 tslint

-0.14

Federal

-0.14

 Pompe

-0.14

 Tutorial

-0.14

ureau

-0.14

é¦

-0.14

 Municip

-0.13

POSITIVE LOGITS

 Schedule

0.21

 Scottish

0.20

 Scotland

0.19

 Directions

0.19

 Welsh

0.19

 disap

0.19

 Wales

0.18

Schedule

0.17

interop

0.17

 directions

0.16

Activations Density 0.088%

references to legislation and regulatory measures

No Comments

No Known Activations