© 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. 46066
    Prev
    Next
    INDEX
    Explanations

    start

    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
     Xamarin
    -0.07
     Surgical
    -0.07
    /int
    -0.07
     говорит
    -0.06
     activists
    -0.06
    NETWORK
    -0.06
     BAD
    -0.06
     Zum
    -0.06
     dahil
    -0.06
    robe
    -0.06
    POSITIVE LOGITS
    Buying
    0.06
    villa
    0.06
    weed
    0.06
    вен
    0.06
    extAlignment
    0.06
    -handed
    0.06
    ($('.
    0.06
    uil
    0.06
    ópez
    0.06
    ills
    0.06
    Activations Density 0.016%

    No Known Activations