INDEX

Explanations

textual representations of leadership and professional roles

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

èĭ¦

-0.14

Surv

-0.12

izarre

-0.12

addock

-0.12

 ÑģÑĤÑĢÐ°ÑĪ

-0.12

 Ã¶ld

-0.11

æľŃ

-0.11

 scrapy

-0.11

 Ð¾Ð¿Ð°Ñģ

-0.11

å²³

-0.11

POSITIVE LOGITS

 joyful

0.30

 delighted

0.28

 smiles

0.28

joy

0.27

 delight

0.27

 cheerful

0.27

 delightful

0.27

 happiness

0.26

 smiling

0.26

 smile

0.26

Activations Density 0.040%

textual representations of leadership and professional roles

No Comments

No Known Activations