INDEX

Explanations

references to God and religious themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Gods

-0.17

ecast

-0.17

-turned

-0.15

UserRole

-0.14

umber

-0.14

AGO

-0.14

uforia

-0.14

reinterpret

-0.14

nts

-0.13

POSITIVE LOGITS

 himself

0.24

frey

0.23

 Himself

0.21

 Almighty

0.19

dish

0.15

Å¯v

0.15

li

0.15

liness

0.15

 Alone

0.15

èĹ

0.15

Activations Density 0.047%

references to God and religious themes

No Comments

No Known Activations