© 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. 36188
    Prev
    Next
    INDEX
    Explanations

    scanning and movement

    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
     uygu
    -0.07
     hashMap
    -0.06
    opacity
    -0.06
     fwd
    -0.06
    DW
    -0.06
    호
    -0.06
    HSV
    -0.06
     cena
    -0.06
     Md
    -0.06
     porta
    -0.06
    POSITIVE LOGITS
    .Branch
    0.07
     отверсти
    0.06
     depress
    0.06
     besar
    0.06
     Cock
    0.06
    ’S
    0.06
    >The
    0.06
    >(
    0.06
    Resultado
    0.06
    .Xna
    0.06
    Activations Density 0.050%

    No Known Activations