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. 87074
    Prev
    Next
    INDEX
    Explanations

    code

    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
    utors
    -0.07
    rible
    -0.06
    ปกครอง
    -0.06
    .М
    -0.06
    вал
    -0.06
     This
    -0.06
    �
    -0.06
    .TRA
    -0.06
    phere
    -0.06
     ऐ
    -0.06
    POSITIVE LOGITS
     secondo
    0.07
    .son
    0.06
     metab
    0.06
     Aspen
    0.06
    urma
    0.06
     cest
    0.06
     genus
    0.06
     sca
    0.06
     cyk
    0.06
    .tp
    0.06
    Activations Density 0.018%

    No Known Activations