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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 42709
    Prev
    Next
    INDEX
    Explanations

    marker

    np_max-act · gemini-2.0-flash

    The neuron activates on code tokens naming Google/MapKit map objects, properties, and operations (e.g. mapView, cameraPosition, marker, settings.myLocationEnabled), i.e. things referring to map API elements.

    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
     drunk
    -0.06
    Budget
    -0.06
     BANK
    -0.06
    低
    -0.06
     debts
    -0.06
    Phones
    -0.06
    .imp
    -0.05
     cuisine
    -0.05
    ансов
    -0.05
    _SEPARATOR
    -0.05
    POSITIVE LOGITS
     Vid
    0.07
    Добав
    0.07
     maxY
    0.07
     máme
    0.07
     utilize
    0.07
     دلیل
    0.07
     pem
    0.07
     pojist
    0.07
     �
    0.06
     coax
    0.06
    Activations Density 0.007%

    No Known Activations