© 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. 15-RESID-POST-AA
    11. 45181
    Prev
    Next
    INDEX
    Explanations

    masks

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .hy
    -0.07
     madd
    -0.07
     MU
    -0.07
     Cabinets
    -0.06
    ád
    -0.06
    tan
    -0.06
     cabinets
    -0.06
    ubernetes
    -0.06
     Cad
    -0.06
    ILog
    -0.06
    POSITIVE LOGITS
    곡
    0.08
    	pr
    0.07
    モデル
    0.06
    gil
    0.06
     ecl
    0.06
    	resolve
    0.06
     curly
    0.06
    啪
    0.06
     UIAlertView
    0.06
     Dataset
    0.06
    Activations Density 0.026%

    No Known Activations