INDEX

Explanations

rom

np_max-act · gemini-2.0-flash

The neuron is detecting mentions of macromolecules (e.g. “mac rom olecules” and related terms).

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

you

-0.07

 panties

-0.07

oment

-0.07

_ENGINE

-0.07

 infantry

-0.06

 tumor

-0.06

what

-0.06

yer

-0.06

 legitimacy

-0.06

vyk

-0.06

POSITIVE LOGITS

ron

0.07

ністю

0.07

RON

0.07

rc

0.07

بات

0.06

 capacidad

0.06

 král

0.06

ropical

0.06

OrDefault

0.06

ων

0.06

Activations Density 0.003%

rom

The neuron is detecting mentions of macromolecules (e.g. “mac rom olecules” and related terms).

No Comments

No Known Activations