INDEX

Explanations

of the

np_max-act · gemini-2.0-flash

The neuron fires on nouns naming chemical reaction processes (terms ending in “-ation” or “-ysis,” e.g., hydrogenation, oxidation, reduction, combustion, catalysis).

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

Negative Logits

_review

-0.07

ีส

-0.07

VIRTUAL

-0.07

介

-0.07

.webkit

-0.07

ोग

-0.06

BLEM

-0.06

Doctor

-0.06

meteor

-0.06

¨ط

-0.06

POSITIVE LOGITS

ansas

0.06

.account

0.06

ông

0.06

acial

0.06

 Conc

0.06

enever

0.06

 Derby

0.06

 jogging

0.06

.listdir

0.06

__(*

0.06

Activations Density 0.017%

of the

The neuron fires on nouns naming chemical reaction processes (terms ending in “-ation” or “-ysis,” e.g., hydrogenation, oxidation, reduction, combustion, catalysis).

No Known Activations

of the

The neuron fires on nouns naming chemical reaction processes (terms ending in “-ation” or “-ysis,” e.g., hydrogenation, oxidation, reduction, combustion, catalysis).

No Known Activations