INDEX

Explanations

affirmations or positive statements about experiences and accomplishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

meric

-0.17

alar

-0.15

ifer

-0.15

eper

-0.14

 harmless

-0.14

 surprise

-0.14

ron

-0.13

might

-0.13

othy

-0.13

 vont

-0.13

POSITIVE LOGITS

 pleasure

0.19

aju

0.17

Ple

0.17

award

0.16

 privilege

0.16

fit

0.15

ignum

0.15

ç³»

0.14

 grat

0.14

chai

0.14

Activations Density 0.092%

affirmations or positive statements about experiences and accomplishments

No Comments

No Known Activations