INDEX

Explanations

donations

np_max-act · gemini-2.0-flash

The neuron flags phrases describing donation or gift-giving options and instructions (e.g. how, when, or by what method to give).

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

 Cliente

-0.07

_hs

-0.07

 logistic

-0.06

Та

-0.06

 Certain

-0.06

Verbose

-0.06

"('

-0.06

tas

-0.06

.Address

-0.06

Ön

-0.06

POSITIVE LOGITS

 celebrates

0.07

 democr

0.07

pil

0.07

Represent

0.07

 первой

0.07

jourd

0.07

บล

0.07

 yıldır

0.07

(android

0.07

 installations

0.07

Activations Density 0.028%

donations

The neuron flags phrases describing donation or gift-giving options and instructions (e.g. how, when, or by what method to give).

No Comments

No Known Activations

donations

The neuron flags phrases describing donation or gift-giving options and instructions (e.g. how, when, or by what method to give).

No Comments

No Known Activations