© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 102196
    Prev
    Next
    INDEX
    Explanations

    legal discretion

    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
    巡
    -0.06
    _parallel
    -0.06
     Frage
    -0.06
    704
    -0.06
     gobierno
    -0.06
     moda
    -0.06
    Python
    -0.06
     Muj
    -0.06
    |min
    -0.06
    .'↵↵
    -0.06
    POSITIVE LOGITS
     THROW
    0.07
    BJECT
    0.07
    Pot
    0.06
    мос
    0.06
    وله
    0.06
     responsive
    0.06
    .yaml
    0.06
    SYSTEM
    0.06
     responsiveness
    0.06
    长
    0.06
    Activations Density 0.003%

    No Known Activations