INDEX

Explanations

locations and regions mentioned in context

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

 Geographic

-0.17

urger

-0.16

oui

-0.15

oge

-0.14

Äĥn

-0.14

 geographic

-0.14

anel

-0.14

usi

-0.14

cip

-0.13

alion

-0.13

POSITIVE LOGITS

 abroad

0.28

 elsewhere

0.27

Else

0.22

 beyond

0.21

 Else

0.20

 Europe

0.17

 worldwide

0.17

eyond

0.17

 neighboring

0.17

Beyond

0.17

Activations Density 0.151%

locations and regions mentioned in context

No Comments

No Known Activations