INDEX

Explanations

references to official titles and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

avana

-0.16

omap

-0.16

å·ŀ

-0.16

apan

-0.16

VG

-0.16

bane

-0.15

 Municip

-0.15

 Strom

-0.15

********************************************************************************

-0.14

uyu

-0.14

POSITIVE LOGITS

 Federal

0.21

 federal

0.20

 Nigeria

0.19

Abu

0.18

Federal

0.18

 Niger

0.17

zen

0.17

 federally

0.16

 Nigerian

0.16

ayar

0.15

Activations Density 0.033%

references to official titles and positions

No Comments

No Known Activations