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. 87059
    Prev
    Next
    INDEX
    Explanations

    entertainment

    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
     TXT
    -0.07
    χεία
    -0.06
    UDIO
    -0.06
     حساب
    -0.06
    産
    -0.06
     حدود
    -0.06
    船
    -0.06
     playa
    -0.06
     mcc
    -0.06
     کمک
    -0.06
    POSITIVE LOGITS
    /qt
    0.06
    >{$
    0.06
    ітет
    0.06
    ي
    0.06
    ěl
    0.06
     kiện
    0.06
     utilizes
    0.06
    ViewHolder
    0.06
    .Attributes
    0.06
     Thanks
    0.06
    Activations Density 0.097%

    No Known Activations