© 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. 41020
    Prev
    Next
    INDEX
    Explanations

    google maps api

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of the Google Maps API (i.e. tokens like “Google,” “Maps,” “API,” and their combination).

    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
    GAME
    -0.06
     loyal
    -0.06
     surtout
    -0.06
    意味
    -0.06
     Medieval
    -0.06
     Fedora
    -0.06
     суду
    -0.06
    Tuy
    -0.06
     eligibility
    -0.06
     PROCUREMENT
    -0.05
    POSITIVE LOGITS
    _float
    0.07
    $form
    0.07
    -notes
    0.07
    inheritDoc
    0.06
    .gnu
    0.06
    _NOW
    0.06
    _,,
    0.06
    þ
    0.06
    naire
    0.06
    $get
    0.06
    Activations Density 0.005%

    No Known Activations