© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 92795
    Prev
    Next
    INDEX
    Explanations

    addSubview

    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
    =float
    -0.07
     oluyor
    -0.07
    Player
    -0.07
     çevre
    -0.07
    prt
    -0.07
    Configuration
    -0.07
     birlikte
    -0.06
     arrival
    -0.06
    ावन
    -0.06
     začala
    -0.06
    POSITIVE LOGITS
     ά
    0.06
     ø
    0.06
     л
    0.06
    (typeof
    0.06
    (reordered
    0.06
    [],
    0.06
    (items
    0.06
     GENERIC
    0.06
    專
    0.05
     gaz
    0.05
    Activations Density 0.008%

    No Known Activations