INDEX

Explanations

phrases related to experiences and activities that promote exploration and enjoyment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ardy

-0.18

undry

-0.15

Ð´Ñı

-0.14

Ã²ng

-0.14

orners

-0.13

addtogroup

-0.13

ê¸°ê°Ģ

-0.13

ãĤ¤ãĤº

-0.13

ograms

-0.13

inson

-0.13

POSITIVE LOGITS

 yourself

0.27

your

0.21

 your

0.21

 yourselves

0.18

ä½łçļĦ

0.18

åĲ§

0.17

 YOUR

0.15

 Yourself

0.15

 vaÅ¡e

0.15

orsch

0.14

Activations Density 0.311%

phrases related to experiences and activities that promote exploration and enjoyment

No Comments

No Known Activations