INDEX

Explanations

imprisonment

np_max-act · gemini-2.0-flash

This neuron activates on legal‐text tokens that specify punishments—particularly imprisonment terms and fines in sentencing provisions.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

legal terms and phrases related to theft and its consequences.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sleeping

-0.06

 اجر

-0.06

 deduct

-0.06

.isUser

-0.06

-*-

-0.06

аки

-0.06

 vibrating

-0.06

 ther

-0.06

quisition

-0.06

 disability

-0.06

POSITIVE LOGITS

Ca

0.07

 stát

0.07

 Girlfriend

0.06

ONSE

0.06

/Admin

0.06

:bold

0.06

 AppMethodBeat

0.06

Sms

0.06

 connexion

0.06

 jong

0.06

Activations Density 0.005%

imprisonment

This neuron activates on legal‐text tokens that specify punishments—particularly imprisonment terms and fines in sentencing provisions.

legal terms and phrases related to theft and its consequences.

No Comments

No Known Activations

imprisonment

This neuron activates on legal‐text tokens that specify punishments—particularly imprisonment terms and fines in sentencing provisions.

legal terms and phrases related to theft and its consequences.

No Comments

No Known Activations