© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 8688
    Prev
    Next
    INDEX
    Explanations

    wherein

    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
    <Player
    -0.06
     valu
    -0.06
     交
    -0.06
     famous
    -0.06
     Kaz
    -0.06
     reactionary
    -0.06
    $action
    -0.06
    〉
    -0.06
     usted
    -0.06
     عرض
    -0.06
    POSITIVE LOGITS
    .Dispose
    0.08
    _LSB
    0.07
    _proto
    0.07
     sap
    0.07
    .B
    0.07
    .Http
    0.07
    /sp
    0.07
    .spin
    0.07
    kins
    0.07
    :/
    0.07
    Activations Density 0.005%

    No Known Activations