Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129423
    Prev
    Next
    INDEX
    Explanations

    OnPropertyChanged

    np_max-act · gemini-2.0-flash

    This neuron detects C# MVVM ViewModel code patterns—specifically declarations of ObservableCollection properties and calls to OnPropertyChanged.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    maal
    -0.06
     жінок
    -0.06
    för
    -0.06
    StrLn
    -0.06
    intptr
    -0.06
     IH
    -0.06
    ULD
    -0.06
     JM
    -0.06
    jom
    -0.06
    _quick
    -0.06
    POSITIVE LOGITS
     RaisePropertyChanged
    0.08
     возмож
    0.07
     OnPropertyChanged
    0.07
     кот
    0.07
    	order
    0.06
     handmade
    0.06
     PARAMETERS
    0.06
     cung
    0.06
     equation
    0.06
     García
    0.06
    Activations Density 0.003%

    No Known Activations