Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87112
    Prev
    Next
    INDEX
    Explanations

    scientific study reports

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     навчання
    -0.07
    CLS
    -0.06
    _FD
    -0.06
     Naz
    -0.06
    _pt
    -0.06
     thì
    -0.06
    cart
    -0.06
    memberof
    -0.06
    TexParameteri
    -0.06
     Europ
    -0.06
    POSITIVE LOGITS
     akce
    0.07
    ्वव
    0.07
    .proj
    0.07
    :%
    0.06
     coverage
    0.06
    ıyı
    0.06
     inorder
    0.06
    oplayer
    0.06
    _producto
    0.06
    .ClientSize
    0.06
    Activations Density 0.038%

    No Known Activations