INDEX

Explanations

is

np_max-act · gemini-2.0-flash

This neuron detects statements of the form “variable is positive,” i.e. expressions asserting that a variable has positive value.

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

tep

-0.06

 ComponentFixture

-0.06

 GUIContent

-0.06

 participate

-0.06

ト

-0.06

kı

-0.06

.gstatic

-0.06

رات

-0.06

вести

-0.06

 servlet

-0.06

POSITIVE LOGITS

 Wildcats

0.07

 third

0.07

 Dynasty

0.07

 Ready

0.07

 circa

0.06

_entry

0.06

 Bent

0.06

{(

0.06

 Naval

0.06

 Clarkson

0.06

Activations Density 0.001%

is

This neuron detects statements of the form “variable is positive,” i.e. expressions asserting that a variable has positive value.

No Comments

No Known Activations