INDEX

Explanations

install

np_max-act · gemini-2.0-flash

The neuron activates on installation and configuration directives in build scripts (e.g. “install” targets and CMAKE_INSTALL_… variables).

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

 molec

-0.07

 Meeting

-0.07

 Macron

-0.06

χε

-0.06

errupted

-0.06

Convertible

-0.06

 meeting

-0.06

لیت

-0.06

طور

-0.06

 psycho

-0.06

POSITIVE LOGITS

九

0.07

 vyžad

0.07

''

0.07

 allowNull

0.07

.Cons

0.07

�

0.06

 understandably

0.06

.stat

0.06

step

0.06

Ply

0.06

Activations Density 0.005%

install

The neuron activates on installation and configuration directives in build scripts (e.g. “install” targets and CMAKE_INSTALL_… variables).

No Comments

No Known Activations