INDEX

Explanations

indicators of suspicion or things that evoke skepticism

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

azen

-0.18

getter

-0.17

łí

-0.16

engu

-0.14

áº»

-0.14

ihat

-0.14

 currencies

-0.13

ingo

-0.13

ask

-0.13

 Ð»Ð¸ÑĪ

-0.13

POSITIVE LOGITS

villa

0.16

 hÃ£

0.15

inho

0.15

afen

0.15

ably

0.14

omal

0.14

profil

0.14

 Abram

0.14

Î®

0.14

stakes

0.14

Activations Density 0.003%

indicators of suspicion or things that evoke skepticism

No Comments

No Known Activations