INDEX

Explanations

references to historical empires and territorial control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

etta

-0.15

xbc

-0.14

attached

-0.14

jac

-0.14

AXB

-0.14

laus

-0.13

aina

-0.13

 Independ

-0.13

jon

-0.13

ace

-0.13

POSITIVE LOGITS

Emp

0.72

Emp

0.70

emp

0.68

 Empire

0.65

 empire

0.60

emp

0.56

 Imper

0.55

.emp

0.54

 imper

0.54

_emp

0.54

Activations Density 0.157%

references to historical empires and territorial control

No Comments

No Known Activations