INDEX

Explanations

parts of devices

np_max-act · gemini-2.0-flash

The neuron activates on words naming physical components or parts of a device (e.g. receptacle, bottom, outlet, lid).

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

Від

-0.07

)]
↵

-0.06

Ce

-0.06

,self

-0.06

 DESCRIPTION

-0.06

CGPoint

-0.06

 redraw

-0.06

 insulation

-0.06

OTO

-0.06

POSITIVE LOGITS

selectAll

0.07

atrix

0.06

 cargar

0.06

 explanatory

0.06

 crime

0.06

aida

0.06

 eclipse

0.06

.StoredProcedure

0.06

 Bayern

0.06

 commun

0.06

Activations Density 0.095%

parts of devices

The neuron activates on words naming physical components or parts of a device (e.g. receptacle, bottom, outlet, lid).

No Comments

No Known Activations