INDEX

Explanations

mentions of individuals, particularly women, within the context of their actions, roles, and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 himself

-0.36

 Himself

-0.24

å¦»

-0.24

 stesso

-0.22

his

-0.21

ä¿Ĭ

-0.20

 ÙĨÙģØ³Ùĩ

-0.19

/she

-0.19

Jr

-0.19

 handsome

-0.19

POSITIVE LOGITS

 herself

0.57

 ÑģÐ°Ð¼Ð°

0.28

 Ð¼Ð¾Ð³Ð»Ð°

0.26

athed

0.24

ovÃ¡

0.24

ä¸Īå¤«

0.24

 Ð´Ð¾Ð»Ð¶Ð½Ð°

0.24

 ÑģÑĤÐ°Ð»Ð°

0.23

/he

0.22

 ÑģÐºÐ°Ð·Ð°Ð»Ð°

0.22

Activations Density 3.095%

mentions of individuals, particularly women, within the context of their actions, roles, and experiences

No Comments

No Known Activations