INDEX

Explanations

references to personal belongings and ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Lifestyle

-0.13

ophe

-0.12

engin

-0.12

èĩ

-0.12

utting

-0.12

orgia

-0.12

coe

-0.12

Ã¶h

-0.12

iÅ¡

-0.12

ogra

-0.12

POSITIVE LOGITS

 ownership

0.86

 Ownership

0.73

ownership

0.72

 owned

0.67

 owning

0.66

Ownership

0.66

 possession

0.63

 owns

0.60

 owner

0.57

 owners

0.57

Activations Density 0.219%

references to personal belongings and ownership

No Comments

No Known Activations