INDEX

Explanations

students

np_max-act · gemini-2.0-flash

This neuron detects the “Students will be able to…” phrasing used in learning-objective statements.

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

�

-0.08

.Hidden

-0.07

_accessor

-0.07

HID

-0.07

 toString

-0.07

 insect

-0.07

Qt

-0.07

.exception

-0.07

.sheet

-0.06

 Timestamp

-0.06

POSITIVE LOGITS

%',

0.07

vyb

0.07

ynomials

0.06

.shows

0.06

 strav

0.06

 апреля

0.06

(Environment

0.06

resar

0.06

确

0.06

 philosophical

0.06

Activations Density 0.027%

students

This neuron detects the “Students will be able to…” phrasing used in learning-objective statements.

No Comments

No Known Activations