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. 102500
    Prev
    Next
    INDEX
    Explanations

    Missing data

    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
    iska
    -0.07
    Mem
    -0.07
     meziná
    -0.07
    Mon
    -0.07
     polygons
    -0.06
     Adidas
    -0.06
     dangerous
    -0.06
    anı
    -0.06
    ávání
    -0.06
     autonom
    -0.06
    POSITIVE LOGITS
    -chart
    0.08
    ليف
    0.07
    ::.
    0.06
    :data
    0.06
    vented
    0.06
     širo
    0.06
    _CART
    0.06
    .summary
    0.06
    capabilities
    0.06
     akin
    0.06
    Activations Density 0.029%

    No Known Activations