INDEX

Explanations

commercial

np_max-act · gemini-2.0-flash

The neuron activates on words naming real‐estate or development use types (e.g. commercial, office, retail, mixed‐use, industrial, residential).

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Room

-0.07

ตำ

-0.07

 vertex

-0.07

MS

-0.07

ิศ

-0.06

 Moon

-0.06

 room

-0.06

 Greece

-0.06

report

-0.06

 vertices

-0.06

POSITIVE LOGITS

approve

0.07

.Cons

0.07

.......

0.06

のだ

0.06

(prog

0.06

","

0.06

.Left

0.06

）。↵

0.06

lis

0.06

.methods

0.06

Activations Density 0.011%

commercial

The neuron activates on words naming real‐estate or development use types (e.g. commercial, office, retail, mixed‐use, industrial, residential).

No Comments

No Known Activations