INDEX

Explanations

phrases indicating collective benefit and altruism

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

ordes

-0.15

deniz

-0.15

insky

-0.15

CTS

-0.14

/mainwindow

-0.14

åł¡

-0.14

_busy

-0.14

æµª

-0.13

é¡į

-0.13

POSITIVE LOGITS

 benefit

0.37

 good

0.36

 common

0.35

 greater

0.32

good

0.30

 Good

0.30

 Benefit

0.30

common

0.28

-good

0.28

/common

0.28

Activations Density 0.098%

phrases indicating collective benefit and altruism

No Comments

No Known Activations