INDEX

Explanations

advice and encouragement for personal growth and self-improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

MOTE

-0.15

greens

-0.15

udge

-0.15

rades

-0.14

tps

-0.14

lis

-0.14

edian

-0.14

ÐµÐ´Ð¸Ð½

-0.14

InMillis

-0.14

ashion

-0.13

POSITIVE LOGITS

 yourself

0.23

 your

0.20

 yourselves

0.19

ä½łçļĦ

0.16

 Yourself

0.16

åĲ§

0.16

0.15

your

0.15

hou

0.14

inh

0.14

Activations Density 1.106%

advice and encouragement for personal growth and self-improvement

No Comments

No Known Activations