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. 87082
    Prev
    Next
    INDEX
    Explanations

    time intervals

    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
     Join
    -0.06
    ,对
    -0.06
     unchecked
    -0.06
     exact
    -0.06
     irgend
    -0.06
    bias
    -0.06
    ).'</
    -0.06
     Failed
    -0.06
    )[
    -0.06
     takes
    -0.06
    POSITIVE LOGITS
     ممن
    0.06
     گوشی
    0.06
     типу
    0.06
    Presentation
    0.06
    genesis
    0.06
    (Runtime
    0.06
    ARATION
    0.06
    „ظ
    0.06
    enství
    0.06
     Hồng
    0.06
    Activations Density 0.008%

    No Known Activations