© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 79116
    Prev
    Next
    INDEX
    Explanations

    principle idea

    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
     Barn
    -0.07
     Excellence
    -0.07
    伯
    -0.06
     왕
    -0.06
     Appliances
    -0.06
    Otherwise
    -0.06
     progress
    -0.06
    -suite
    -0.06
    -defined
    -0.06
    ्र
    -0.06
    POSITIVE LOGITS
     programa
    0.07
    .flush
    0.07
     seq
    0.07
     공
    0.07
     proletariat
    0.06
    _Total
    0.06
     手
    0.06
     thrill
    0.06
    .Validate
    0.06
    ynam
    0.06
    Activations Density 0.031%

    No Known Activations