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. 87106
    Prev
    Next
    INDEX
    Explanations

    Introductions of research papers

    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
    ughters
    -0.07
    �다
    -0.07
     Gavin
    -0.06
     صند
    -0.06
    일본
    -0.06
     AMA
    -0.06
    rych
    -0.06
    urses
    -0.06
     Kaf
    -0.06
     traders
    -0.06
    POSITIVE LOGITS
    <iostream
    0.08
    συ
    0.07
     emerges
    0.06
     refugee
    0.06
     Moreover
    0.06
    ↵  ↵
    0.06
    ังน
    0.06
    IFORM
    0.06
     بعد
    0.06
    Mailer
    0.06
    Activations Density 0.003%

    No Known Activations