INDEX

Explanations

code

np_max-act · gemini-2.0-flash

This neuron activates on form‐validation tokens and state checks (e.g. `.invalid`, `.dirty`, `.touched`, `.errors`, `required`, `minLength`, `maxLength`) in Angular reactive‐form code.

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

γ

-0.07

�

-0.06

 MULTI

-0.06

edula

-0.06

_sigma

-0.06

.Distance

-0.06

фик

-0.06

ALA

-0.06

.warn

-0.06

idebar

-0.06

POSITIVE LOGITS

 drowned

0.08

_Instance

0.07

ildiği

0.07

�

0.07

ive

0.07

�

0.07

 CONS

0.07

��

0.06

้ย

0.06

			↵			↵

0.06

Activations Density 0.028%

code

This neuron activates on form‐validation tokens and state checks (e.g. `.invalid`, `.dirty`, `.touched`, `.errors`, `required`, `minLength`, `maxLength`) in Angular reactive‐form code.

No Comments

No Known Activations

code

This neuron activates on form‐validation tokens and state checks (e.g. `.invalid`, `.dirty`, `.touched`, `.errors`, `required`, `minLength`, `maxLength`) in Angular reactive‐form code.

No Comments

No Known Activations