INDEX

Explanations

references to self-directed language and concepts of self

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 itself

-0.27

 themselves

-0.20

 himself

-0.20

 ourselves

-0.18

nc

-0.17

 herself

-0.17

 Himself

-0.17

 zich

-0.16

 oneself

-0.15

 ÑģÐ°Ð¼Ð°

-0.15

POSITIVE LOGITS

zelf

0.30

-mÃªme

0.22

Ã¤nd

0.20

/us

0.18

/self

0.18

/my

0.18

elves

0.18

.StackTrace

0.16

embro

0.16

IPP

0.16

Activations Density 0.072%

references to self-directed language and concepts of self

No Comments

No Known Activations