© 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. 19-RESID-POST-AA
    11. 121793
    Prev
    Next
    INDEX
    Explanations

    ouse

    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
    “What
    -0.07
     helf
    -0.07
    'I
    -0.07
     diabetic
    -0.06
     período
    -0.06
     questi
    -0.06
     treffen
    -0.06
     протягом
    -0.06
    amız
    -0.06
     halten
    -0.06
    POSITIVE LOGITS
    (suffix
    0.07
    .Safe
    0.07
    equip
    0.07
    .messaging
    0.07
     Print
    0.07
    _aff
    0.07
    .additional
    0.07
    VISION
    0.06
    мах
    0.06
    _AF
    0.06
    Activations Density 0.000%

    No Known Activations