© 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. 20327
    Prev
    Next
    INDEX
    Explanations

    success

    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
     unpopular
    -0.06
     absolutely
    -0.06
     retain
    -0.06
    制造
    -0.06
     cooks
    -0.06
    _LOOKUP
    -0.06
     обст
    -0.06
    الق
    -0.06
    中的
    -0.06
    =@"
    -0.05
    POSITIVE LOGITS
    _wifi
    0.07
    annis
    0.07
    idae
    0.06
     Cent
    0.06
     sincerely
    0.06
    rowse
    0.06
     موفق
    0.06
     fibers
    0.06
     gar
    0.06
    .Book
    0.06
    Activations Density 0.005%

    No Known Activations