INDEX

Explanations

zen

np_max-act · gemini-2.0-flash

The neuron activates on mentions of “benzene” (e.g. in chemical names containing the substring benzene), effectively detecting references to benzene rings or benzene-derived compounds.

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

 SHOW

-0.07

ContentSize

-0.06

 Salt

-0.06

 CONTACT

-0.06

 Mobility

-0.06

 mobility

-0.06

	layout

-0.06

 AJAX

-0.05

Separator

-0.05

OperationContract

-0.05

POSITIVE LOGITS

業

0.08

cran

0.07

ική

0.07

//*

0.07

 commonly

0.07

زم

0.07

loquent

0.07

PIP

0.07

 kalp

0.06

doch

0.06

Activations Density 0.015%

zen

The neuron activates on mentions of “benzene” (e.g. in chemical names containing the substring benzene), effectively detecting references to benzene rings or benzene-derived compounds.

No Comments

No Known Activations

zen

The neuron activates on mentions of “benzene” (e.g. in chemical names containing the substring benzene), effectively detecting references to benzene rings or benzene-derived compounds.

No Comments

No Known Activations