INDEX

Explanations

instances of decision-making and personal agency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

htar

-0.14

fav

-0.14

 pause

-0.14

NotEmpty

-0.14

alent

-0.14

 fraction

-0.13

eum

-0.13

ailable

-0.13

cl

-0.13

 Bout

-0.13

POSITIVE LOGITS

ooke

0.17

QUI

0.17

reta

0.16

fÃ©

0.16

 ignorance

0.15

ign

0.15

igon

0.15

Quiet

0.14

 eiusmod

0.14

lek

0.14

Activations Density 0.229%

instances of decision-making and personal agency

No Comments

No Known Activations