INDEX

Explanations

places

np_max-act · gemini-2.0-flash

The neuron activates on category lines that mention a specific year (four-digit) in “establishments” or “disestablishments” labels.

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

SYSTEM

-0.06

_REGION

-0.06

Mean

-0.06

AndGet

-0.06

 уровня

-0.06

 removeFrom

-0.06

вин

-0.06

WND

-0.06

_k

-0.06

Inserted

-0.06

POSITIVE LOGITS

 май

0.07

youtu

0.06

})();↵

0.06

 SQLite

0.06

UIF

0.06

_SECURE

0.06

 intrig

0.06

 ))}↵

0.06

_Name

0.06

 SizedBox

0.06

Activations Density 0.002%

places

The neuron activates on category lines that mention a specific year (four-digit) in “establishments” or “disestablishments” labels.

No Comments

No Known Activations