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. 87029
    Prev
    Next
    INDEX
    Explanations

    the

    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
    _hero
    -0.06
    .getSelection
    -0.06
     参考
    -0.06
    unlikely
    -0.06
    .place
    -0.06
    reshape
    -0.06
    _Params
    -0.06
     compatible
    -0.06
    _iteration
    -0.06
    Share
    -0.06
    POSITIVE LOGITS
     группы
    0.07
    PackageManager
    0.07
    ливих
    0.06
    osaic
    0.06
    ateurs
    0.06
    关
    0.06
    らない
    0.06
     点
    0.06
     sp
    0.06
    =_("
    0.06
    Activations Density 0.006%

    No Known Activations