INDEX

Explanations

references to binaries and dichotomies, especially those related to gender and societal roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

oldt

-0.17

olib

-0.16

-0.14

inu

-0.14

factory

-0.14

 jack

-0.14

.ax

-0.14

 factory

-0.14

itag

-0.14

aze

-0.14

POSITIVE LOGITS

Ø³Ø§Ø³

0.19

/Application

0.15

inputEmail

0.14

à¥įà¤®à¤ķ

0.14

)prepare

0.14

é¤

0.14

updatedAt

0.14

_continuous

0.14

OSH

0.14

DataExchange

0.14

Activations Density 0.179%

references to binaries and dichotomies, especially those related to gender and societal roles

No Comments

No Known Activations