INDEX

Explanations

references to LGBTQ+ identity and representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

anken

-0.14

chantment

-0.13

mlink

-0.13

odial

-0.13

 nutrient

-0.12

ullan

-0.12

ossa

-0.12

å²¡

-0.12

aurant

-0.12

uang

-0.12

POSITIVE LOGITS

 LGBT

0.68

 LGBTQ

0.66

gay

0.66

 queer

0.60

 lesbian

0.60

 Lesbian

0.59

 homosexual

0.58

Gay

0.57

 gays

0.56

gay

0.56

Activations Density 0.527%

references to LGBTQ+ identity and representation

No Comments

No Known Activations