INDEX

Explanations

references to the concept of "home" and the search for belonging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

osten

-0.15

usch

-0.14

clin

-0.14

rax

-0.13

phan

-0.13

 Hiring

-0.13

.localized

-0.13

 Basement

-0.13

entes

-0.13

OLON

-0.13

POSITIVE LOGITS

 home

0.62

home

0.50

 homes

0.46

 HOME

0.45

-home

0.43

.home

0.41

 Home

0.41

Home

0.40

_home

0.39

HOME

0.39

Activations Density 0.149%

references to the concept of "home" and the search for belonging

No Comments

No Known Activations