INDEX

Explanations

references to gay identity and LGBTQ+ issues

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

cker

-0.19

inus

-0.17

sg

-0.17

ÑģÑĤÐ¸Ð½

-0.16

rÃ¡l

-0.16

 homosexuals

-0.15

å¸¯

-0.15

 gays

-0.15

_SECURITY

-0.15

 LGBT

-0.15

POSITIVE LOGITS

dar

0.30

-rights

0.25

lord

0.24

-friendly

0.24

 rights

0.23

bor

0.23

 pride

0.22

/trans

0.22

 friendly

0.21

atri

0.21

Activations Density 0.017%

references to gay identity and LGBTQ+ issues

No Comments

No Known Activations