INDEX

Explanations

income

np_max-act · gemini-2.0-flash

The neuron specifically detects the occurrence of the word “income,” often when it appears as a heading or key label.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 server

-0.08

 Server

-0.08

 Walter

-0.07

Al

-0.07

Bal

-0.07

 villain

-0.07

‌ال

-0.07

ератор

-0.07

 forecasts

-0.06

 speculated

-0.06

POSITIVE LOGITS

 income

0.14

 Income

0.14

-income

0.11

Income

0.10

income

0.10

 incomes

0.09

 Hancock

0.07

 доход

0.07

ime

0.07

 Lime

0.07

Activations Density 0.008%

income

The neuron specifically detects the occurrence of the word “income,” often when it appears as a heading or key label.

No Comments

No Known Activations

income

The neuron specifically detects the occurrence of the word “income,” often when it appears as a heading or key label.

No Comments

No Known Activations