© 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. 27-RESID-POST-AA
    11. 12525
    Prev
    Next
    INDEX
    Explanations

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    руз
    -0.07
     justified
    -0.07
    那么
    -0.06
    약
    -0.06
     moreover
    -0.06
    since
    -0.06
     manera
    -0.06
    _Group
    -0.06
    کرد
    -0.06
     vnitř
    -0.06
    POSITIVE LOGITS
    _media
    0.07
    logged
    0.07
    .getSimpleName
    0.07
    sthrough
    0.07
    ansible
    0.07
     BJP
    0.07
     대행
    0.06
     scheduler
    0.06
    ounge
    0.06
     pulse
    0.06
    Activations Density 0.023%

    No Known Activations