INDEX

Explanations

references to rarity or uncommon events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

å¼ĺ

-0.15

 loose

-0.15

ç²Ĺ

-0.15

mrb

-0.14

 rough

-0.14

ä¹ħ

-0.14

atures

-0.14

esk

-0.14

 Leer

-0.13

hurst

-0.13

POSITIVE LOGITS

 Deck

0.16

uto

0.16

?type

0.15

faction

0.15

pedia

0.14

åĽł

0.14

ìŀ¥

0.13

tero

0.13

urma

0.13

orld

0.13

Activations Density 0.081%

references to rarity or uncommon events

No Comments

No Known Activations