© 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. 46067
    Prev
    Next
    INDEX
    Explanations

    Lists/Announcements

    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
    (pattern
    -0.07
     Axe
    -0.07
    user
    -0.07
     lựa
    -0.07
    USER
    -0.07
    etical
    -0.06
    isol
    -0.06
     Century
    -0.06
    :[
    -0.06
    руют
    -0.06
    POSITIVE LOGITS
     classname
    0.07
     disparate
    0.06
     �
    0.06
    upal
    0.06
     cerca
    0.06
     endregion
    0.06
     や
    0.06
     zwar
    0.06
     leggings
    0.06
     TIFF
    0.06
    Activations Density 0.010%

    No Known Activations