© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 45556
    Prev
    Next
    INDEX
    Explanations

    census

    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
    Negative Logits
    clusive
    -0.06
    ammed
    -0.06
    igits
    -0.06
    abad
    -0.06
     depletion
    -0.06
    rms
    -0.06
     Garn
    -0.05
    uers
    -0.05
    IVES
    -0.05
     bride
    -0.05
    POSITIVE LOGITS
     {})
    0.07
    aných
    0.07
     Tarih
    0.07
    itorio
    0.07
     Transition
    0.07
    etections
    0.07
    _SW
    0.07
     imprisonment
    0.07
    ("/")↵
    0.07
     sw
    0.07
    Activations Density 0.005%

    No Known Activations