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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27-RESID-POST-AA
    11. 11584
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Form
    -0.07
     os
    -0.07
    .coin
    -0.06
     서버
    -0.06
    AccessType
    -0.06
     प
    -0.06
    _dm
    -0.06
    	JLabel
    -0.06
    (login
    -0.06
     ThreadPool
    -0.06
    POSITIVE LOGITS
    .'</
    0.07
     суспіль
    0.07
     العق
    0.07
    říd
    0.07
    aisy
    0.06
    arte
    0.06
    寶
    0.06
     العربي
    0.06
    pard
    0.06
    eting
    0.06
    Activations Density 0.101%

    No Known Activations