© 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. 15-RESID-POST-AA
    11. 27589
    Prev
    Next
    INDEX
    Explanations

    Peppers

    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
     SATA
    -0.06
    ViewPager
    -0.06
    	↵
    -0.06
    ета
    -0.06
     Nokia
    -0.06
    아이
    -0.06
     يش
    -0.06
     wreckage
    -0.06
    _upgrade
    -0.06
     ر
    -0.06
    POSITIVE LOGITS
    writing
    0.07
     awaiting
    0.07
    .div
    0.07
    cert
    0.07
     writing
    0.06
     distinctive
    0.06
    ибли
    0.06
    _ED
    0.06
     faculty
    0.06
    -document
    0.06
    Activations Density 0.046%

    No Known Activations