© 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. 43982
    Prev
    Next
    INDEX
    Explanations

    rus

    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
     MOS
    -0.07
    ######↵
    -0.07
    actoring
    -0.07
     PTS
    -0.07
     Philosoph
    -0.06
     biodiversity
    -0.06
     особлив
    -0.06
     poly
    -0.06
     maks
    -0.06
     οικο
    -0.06
    POSITIVE LOGITS
     Graham
    0.09
     Grim
    0.08
     cr
    0.08
     Crawford
    0.08
     Griffin
    0.08
     Drum
    0.07
     Drake
    0.07
     Cri
    0.07
     Kris
    0.07
     crust
    0.07
    Activations Density 0.392%

    No Known Activations