INDEX

Explanations

references to specific literary works and their authors, especially focused on George Orwell's "1984."

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

pras

-0.15

 Shutterstock

-0.15

.vote

-0.15

äºĭåĭĻ

-0.14

_PAYLOAD

-0.14

_Syntax

-0.14

 INTERRUPTION

-0.14

Ø®Ø¨Ø±

-0.14

@nate

-0.13

.partner

-0.13

POSITIVE LOGITS

 Essay

0.30

 essay

0.29

 assignment

0.28

 Assignment

0.28

Essay

0.28

assignment

0.26

essay

0.24

Assignment

0.24

.assignment

0.23

 ASSIGN

0.23

Activations Density 0.178%

references to specific literary works and their authors, especially focused on George Orwell's "1984."

No Comments

No Known Activations