INDEX

Explanations

phrases related to bias in various contexts

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

 Baltimore

-0.21

 Kansas

-0.18

Kansas

-0.17

 Worcester

-0.17

 Nancy

-0.16

 Maryland

-0.15

 Arkansas

-0.15

 Lowell

-0.15

illac

-0.15

 Massachusetts

-0.15

POSITIVE LOGITS

 Titan

0.39

 Titans

0.39

 titan

0.37

tit

0.31

Titan

0.29

 Attack

0.28

Tit

0.28

Tit

0.27

 Levi

0.27

 Survey

0.24

Activations Density 0.002%

phrases related to bias in various contexts

No Comments

No Known Activations