INDEX

Explanations

references to mentorship and personal growth

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

opak

-0.12

ä»ĸåĢĳ

-0.11

 themselves

-0.11

his

-0.11

 knull

-0.11

ÐµÑĤÑĥ

-0.11

 jste

-0.11

 byste

-0.11

 ÑģÐ°Ð¼Ð¸

-0.11

 nÄĽj

-0.11

POSITIVE LOGITS

1.16

my

0.90

 myself

0.79

0.77

æĪĳ

0.65

 tÃ´i

0.64

,I

0.62

Ive

0.61

my

0.59

ï¼ĮæĪĳ

0.59

Activations Density 2.922%

references to mentorship and personal growth

No Comments

No Known Activations