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. 81316
    Prev
    Next
    INDEX
    Explanations

    /

    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
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ‌شد
    -0.06
    "]);
    -0.06
    產品
    -0.06
     сф
    -0.06
    VectorXd
    -0.06
     Swords
    -0.06
    ИТ
    -0.06
    드립니다
    -0.06
    ौकर
    -0.06
    僅
    -0.05
    POSITIVE LOGITS
    .Group
    0.08
     Listener
    0.07
     mutate
    0.07
    .setdefault
    0.07
    ute
    0.07
     activating
    0.07
     scaling
    0.07
    categoryId
    0.07
     CBC
    0.07
     palate
    0.07
    Activations Density 0.001%

    No Known Activations