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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 128046
    Prev
    Next
    INDEX
    Explanations

    verifying and visiting

    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
     {
    
    ↵
    -0.07
    "indices
    -0.06
    Lets
    -0.06
     Progressive
    -0.06
     midfield
    -0.06
    _TASK
    -0.06
     гаран
    -0.06
     CAM
    -0.06
    VID
    -0.06
     consultancy
    -0.06
    POSITIVE LOGITS
    stří
    0.08
    ackBar
    0.07
     пл
    0.06
    .dirty
    0.06
     jQuery
    0.06
     сайте
    0.06
    Subscription
    0.06
    bb
    0.06
     minWidth
    0.06
     GLFW
    0.06
    Activations Density 0.014%

    No Known Activations