INDEX

Explanations

positive descriptions of children and their experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

illez

-0.16

resher

-0.15

 Pregn

-0.15

ä¸Īå¤«

-0.15

 married

-0.15

 celib

-0.15

 pregnant

-0.14

 ladies

-0.14

ipur

-0.14

 Ladies

-0.14

POSITIVE LOGITS

 innocence

0.21

 learning

0.21

 school

0.20

 todd

0.19

 inher

0.18

learning

0.18

 sibling

0.18

 prec

0.18

 innoc

0.17

 siblings

0.17

Activations Density 0.520%

positive descriptions of children and their experiences

No Comments

No Known Activations