© 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. 75850
    Prev
    Next
    INDEX
    Explanations

    sign

    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
    .Student
    -0.07
     Civilization
    -0.07
    Cop
    -0.07
     Sas
    -0.07
    เวอร
    -0.06
    iska
    -0.06
     ответствен
    -0.06
     области
    -0.06
     المدر
    -0.06
     Swe
    -0.06
    POSITIVE LOGITS
    etection
    0.08
     qDebug
    0.06
     đào
    0.06
    claration
    0.06
     Took
    0.06
      
    0.06
    slashes
    0.06
     refusing
    0.06
    ambi
    0.06
     žád
    0.06
    Activations Density 0.018%

    No Known Activations