Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 50424
    Prev
    Next
    INDEX
    Explanations

    literature

    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
    _pid
    -0.07
    kemiz
    -0.06
     국제
    -0.06
    Toolbar
    -0.06
     投
    -0.06
     skeptic
    -0.06
     Lockheed
    -0.06
     �
    -0.06
    (calendar
    -0.06
     kå
    -0.06
    POSITIVE LOGITS
    ('/');↵
    0.07
    ecial
    0.07
    //{↵
    0.07
    (background
    0.06
    there
    0.06
     attain
    0.06
    مارات
    0.06
    phot
    0.06
    Nh
    0.06
    HorizontalAlignment
    0.06
    Activations Density 0.049%

    No Known Activations