© 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. 36083
    Prev
    Next
    INDEX
    Explanations

    factors/causes

    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
     руб
    -0.07
     IData
    -0.06
    cal
    -0.06
     revolver
    -0.06
     bitmap
    -0.06
     rob
    -0.06
     Кост
    -0.06
     कम
    -0.06
     Kingdom
    -0.06
    екс
    -0.06
    POSITIVE LOGITS
    vala
    0.08
    wegian
    0.07
    _keeper
    0.07
    (newValue
    0.07
    /shared
    0.07
    вищ
    0.07
     групи
    0.07
     başlay
    0.06
    ﾊ
    0.06
     дости
    0.06
    Activations Density 0.126%

    No Known Activations