INDEX

Explanations

restaurant

np_max-act · gemini-2.0-flash

This neuron activates on mentions of “restaurant” (in any casing or as part of related tags like “Restaurants”).

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

 gaze

-0.07

Core

-0.07

 Core

-0.07

-Day

-0.07

Pie

-0.07

 coils

-0.06

 Gold

-0.06

 GPIO

-0.06

 dung

-0.06

Jump

-0.06

POSITIVE LOGITS

 restaurant

0.11

 restaurants

0.11

 McDonald

0.09

restaurant

0.08

.artist

0.08

 Restaurant

0.08

�

0.08

Restaurant

0.08

rist

0.07

istro

0.07

Activations Density 0.009%

restaurant

This neuron activates on mentions of “restaurant” (in any casing or as part of related tags like “Restaurants”).

No Comments

No Known Activations