INDEX

Explanations

concepts related to equality and dignity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-0.15

apan

-0.15

 Mellon

-0.14

 Jaune

-0.14

 Underground

-0.14

ocz

-0.14

intptr

-0.14

/icons

-0.14

incoming

-0.13

POSITIVE LOGITS

 human

0.31

 dignity

0.31

 Human

0.28

human

0.25

Human

0.25

 dign

0.25

 worth

0.24

 equal

0.22

UMAN

0.21

-human

0.20

Activations Density 0.147%

concepts related to equality and dignity

No Comments

No Known Activations