INDEX

Explanations

phrases related to fairness and honesty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ELLOW

-0.15

SSERT

-0.15

uem

-0.14

astos

-0.14

ego

-0.14

ecess

-0.14

esinden

-0.14

ÏĦÎŃ

-0.14

rtl

-0.14

 crim

-0.13

POSITIVE LOGITS

 fairness

0.22

 fair

0.18

fair

0.17

oppel

0.17

 Fair

0.17

 Fortune

0.16

 credit

0.16

itzer

0.15

 Paren

0.14

Fair

0.14

Activations Density 0.070%

phrases related to fairness and honesty

No Comments

No Known Activations