INDEX

Explanations

references to historical geographical contexts and empires

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

obby

-0.15

ynom

-0.15

pb

-0.15

 Alger

-0.15

 suburban

-0.15

ulas

-0.14

quito

-0.14

asonic

-0.13

ula

-0.13

ared

-0.13

POSITIVE LOGITS

ERICA

0.20

 lands

0.19

 Terra

0.18

 territory

0.17

uria

0.17

oland

0.17

Ð»Ð°Ð½Ð´

0.16

 Arabia

0.16

 territories

0.16

olland

0.15

Activations Density 0.216%

references to historical geographical contexts and empires

No Comments

No Known Activations