INDEX

Explanations

references to individuality and personal expression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Adopt

-0.16

á»įng

-0.16

ibre

-0.15

 Credential

-0.14

amed

-0.14

iko

-0.14

 anon

-0.14

arious

-0.14

Anonymous

-0.13

iei

-0.13

POSITIVE LOGITS

 personal

0.24

 interpretation

0.23

personal

0.22

 interpretations

0.22

 Interpret

0.20

interpret

0.20

Personal

0.20

 Personal

0.20

 autonomy

0.19

 opinion

0.18

Activations Density 0.023%

references to individuality and personal expression

No Comments

No Known Activations