INDEX

Explanations

references to specific animated series or family-oriented content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

raud

-0.18

ainer

-0.17

eyin

-0.17

ivi

-0.15

 erotik

-0.15

imdi

-0.15

ominator

-0.14

æ³Ĭ

-0.14

 prostitu

-0.14

Ã»

-0.14

POSITIVE LOGITS

 Mort

0.30

 mortal

0.25

Sab

0.24

 Gomez

0.24

Add

0.24

Sab

0.23

mort

0.22

 mort

0.22

-mort

0.22

 Salem

0.19

Activations Density 0.002%

references to specific animated series or family-oriented content

No Comments

No Known Activations