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. 15-RESID-POST-AA
    6. 52430
    Prev
    Next
    INDEX
    Explanations

    ан

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    true
    -0.06
    )}"↵
    -0.06
    责任
    -0.06
    ()));↵
    -0.06
     Dom
    -0.06
    ıza
    -0.06
    preferences
    -0.06
     Williamson
    -0.06
     syn
    -0.06
     مکانی
    -0.06
    POSITIVE LOGITS
    erville
    0.08
    erchant
    0.07
    OnClick
    0.07
    OC
    0.06
    urse
    0.06
    currentTime
    0.06
    .ini
    0.06
     إلي
    0.06
    airy
    0.06
     商
    0.06
    Activations Density 0.314%

    No Known Activations