INDEX

Explanations

D

np_max-act · gemini-2.0-flash

This neuron activates on the standalone capital letter “D” used as the district‐court designator in legal case citations.

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

 Winners

-0.07

vironments

-0.07

tac

-0.07

 systematic

-0.06

 constraints

-0.06

 sensors

-0.06

 switches

-0.06

-figure

-0.06

observable

-0.06

POSITIVE LOGITS

__(*

0.06

 outpost

0.06

MatrixXd

0.06

 pagan

0.06

 IData

0.06

 pré

0.06

演

0.06

 setVisible

0.06

 curtains

0.06

_Group

0.06

Activations Density 0.001%

D

This neuron activates on the standalone capital letter “D” used as the district‐court designator in legal case citations.

No Comments

No Known Activations