INDEX

Explanations

to

np_max-act · gemini-2.0-flash

The neuron activates on words that express legal obligation or requirement (e.g. “required,” “must,” “obligation”).

oai_token-act-pair · o4-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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.buffer

-0.07

 contour

-0.06

 Journey

-0.06

 Kills

-0.06

Dragging

-0.06

proved

-0.06

비

-0.06

itimate

-0.06

งค

-0.06

bag

-0.06

POSITIVE LOGITS

__)

0.07

'],['

0.07

 bás

0.06

优势

0.06

 özgür

0.06

uns

0.06

_FOUND

0.06

PREFIX

0.06

 AssemblyProduct

0.06

.Ph

0.06

Activations Density 0.013%

to

The neuron activates on words that express legal obligation or requirement (e.g. “required,” “must,” “obligation”).

No Comments

No Known Activations