INDEX

Explanations

references to global locations and their accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

uite

-0.15

 Vill

-0.15

ertz

-0.15

Ĺı

-0.14

BTN

-0.14

atham

-0.14

 Morav

-0.14

ãĥ¬ãĥĥãĥĪ

-0.14

 Ethiopian

-0.13

²

-0.13

POSITIVE LOGITS

UK

0.31

UK

0.26

 countries

0.22

USA

0.19

 Britain

0.19

uk

0.18

 Canada

0.18

US

0.18

 Countries

0.18

 country

0.18

Activations Density 0.232%

references to global locations and their accessibility

No Comments

No Known Activations