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. 19-RESID-POST-AA
    6. 83400
    Prev
    Next
    INDEX
    Explanations

    phone number formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    えば
    -0.07
    _interfaces
    -0.07
     organism
    -0.07
    运
    -0.07
    _MALLOC
    -0.06
    (et
    -0.06
     هل
    -0.06
    /(
    -0.06
    ып
    -0.06
    aston
    -0.06
    POSITIVE LOGITS
    IBILITY
    0.07
     oğlu
    0.06
     велич
    0.06
    stood
    0.06
    olvimento
    0.06
    Spe
    0.06
     bist
    0.06
    :UIButtonTypeCustom
    0.06
    duto
    0.06
    atı
    0.06
    Activations Density 0.021%

    No Known Activations