INDEX

Explanations

phrases indicating requests or demands from authority figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 contr

-0.19

-0.15

 semiclassical

-0.14

rella

-0.14

alia

-0.14

 CONTR

-0.13

veys

-0.13

POSITIVE LOGITS

alink

0.16

anlÄ±

0.15

å³

0.15

 PureComponent

0.14

ev

0.14

anoi

0.14

Ã¼c

0.14

oho

0.13

ighet

0.13

chie

0.13

Activations Density 0.059%

phrases indicating requests or demands from authority figures

No Comments

No Known Activations