INDEX

Explanations

negative characteristics and descriptors of individuals, particularly focusing on traits like sexism and narcissism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

lee

-0.16

ongs

-0.15

 person

-0.15

Ø±Ùħ

-0.15

asma

-0.15

Worker

-0.15

 Person

-0.14

rics

-0.14

 Bias

-0.14

eza

-0.14

POSITIVE LOGITS

odash

0.19

git

0.19

 trouble

0.19

 recl

0.18

 brute

0.18

 cipher

0.18

 dile

0.18

 lush

0.18

 stereotype

0.17

 tough

0.17

Activations Density 0.219%

negative characteristics and descriptors of individuals, particularly focusing on traits like sexism and narcissism

No Comments

No Known Activations