© 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. 87259
    Prev
    Next
    INDEX
    Explanations

    Pakistani names/locations

    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
     мені
    -0.07
    	diff
    -0.06
     cinematic
    -0.06
     다운
    -0.06
     marker
    -0.06
    /settingsdialog
    -0.06
    	des
    -0.06
    [col
    -0.06
     kì
    -0.06
    [a
    -0.06
    POSITIVE LOGITS
     unpaid
    0.06
    ++)↵
    0.06
     upt
    0.06
    ighb
    0.06
    ifik
    0.06
     copyrights
    0.06
     istediğiniz
    0.06
    507
    0.06
    ARN
    0.06
     Too
    0.06
    Activations Density 0.043%

    No Known Activations