© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 105450
    Prev
    Next
    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on “import” lines that bring in Android UI or Google Play services/Maps packages (e.g. android.widget or com.google.android.gms.*).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code related to Android application development.

    oai_token-act-pair · gpt-4o-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
     ClassNotFoundException
    -0.07
     CircularProgress
    -0.06
    	method
    -0.06
    _json
    -0.06
    <Element
    -0.06
     Giants
    -0.06
    Logger
    -0.06
     Мі
    -0.06
    UpdatedAt
    -0.06
    Weight
    -0.06
    POSITIVE LOGITS
     редак
    0.07
     scala
    0.07
    epy
    0.07
    925
    0.07
    essler
    0.06
    402
    0.06
     estates
    0.06
     digit
    0.06
     vrch
    0.06
    (tid
    0.06
    Activations Density 0.018%

    No Known Activations