INDEX

Explanations

references to anti-discrimination policies and practices

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

 racially

-0.19

 racist

-0.18

 racism

-0.18

Rac

-0.18

racial

-0.17

_tD

-0.15

eg

-0.15

assi

-0.15

 racing

-0.14

oltip

-0.14

POSITIVE LOGITS

 veteran

0.28

 pregnancy

0.24

 Veteran

0.22

 veter

0.22

 creed

0.22

 veterans

0.21

preg

0.20

 protected

0.20

 Protected

0.20

 disability

0.20

Activations Density 0.017%

references to anti-discrimination policies and practices

No Comments

No Known Activations