INDEX

Explanations

references to religious institutions and their representatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Orthodox

-0.16

asmus

-0.16

 Mormon

-0.15

XT

-0.15

åı·

-0.15

onto

-0.15

Orth

-0.14

æİĪ

-0.14

 Mormons

-0.14

 Katz

-0.14

POSITIVE LOGITS

 Provincial

0.23

 Superior

0.23

 Province

0.23

nov

0.23

Province

0.23

 provinc

0.22

 Cong

0.22

 Brothers

0.22

 superior

0.21

 province

0.21

Activations Density 0.043%

references to religious institutions and their representatives

No Comments

No Known Activations