© 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. 15-RESID-POST-AA
    6. 128783
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ブル
    -0.07
     campos
    -0.07
     Warehouse
    -0.07
     neurological
    -0.06
     relentlessly
    -0.06
    ада
    -0.06
    áfico
    -0.06
     нор
    -0.06
    .player
    -0.06
    ////////////////////////////////////////////////////////
    -0.06
    POSITIVE LOGITS
    乡
    0.06
     King
    0.06
    RON
    0.06
    #End
    0.06
    Odd
    0.06
    gre
    0.06
     Vul
    0.06
    ONUS
    0.06
     OLD
    0.06
     ');
    0.06
    Activations Density 0.000%

    No Known Activations