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. 87044
    Prev
    Next
    INDEX
    Explanations

    proper

    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
     OB
    -0.07
     перег
    -0.06
    .failed
    -0.06
    075
    -0.06
     свої
    -0.06
    cona
    -0.06
     (*.
    -0.06
     beer
    -0.06
    ộp
    -0.06
     contamin
    -0.06
    POSITIVE LOGITS
     उपय
    0.07
     odpowied
    0.07
    σμό
    0.06
    nnen
    0.06
     treated
    0.06
     Đ
    0.06
    .ServiceModel
    0.06
     disposition
    0.06
     talep
    0.06
    .models
    0.06
    Activations Density 0.014%

    No Known Activations