INDEX

Explanations

references to maps and geographic data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÐŁÐļ

-0.16

 Crescent

-0.14

.desktop

-0.14

eczy

-0.14

 Pictures

-0.14

allest

-0.14

ricks

-0.13

tier

-0.13

 ranks

-0.13

èŃ·

-0.13

POSITIVE LOGITS

map

0.31

 maps

0.30

Map

0.30

 mapping

0.28

 scale

0.28

 mapa

0.27

 Mapping

0.26

 Sheet

0.26

 cart

0.26

map

0.26

Activations Density 0.029%

references to maps and geographic data

No Comments

No Known Activations