© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 84825
    Prev
    Next
    INDEX
    Explanations

    code quotation marks/brackets

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     customers
    -0.07
     taste
    -0.07
     boarding
    -0.07
     continents
    -0.07
    Someone
    -0.06
    _PROD
    -0.06
     emphasize
    -0.06
     deduct
    -0.06
     stomach
    -0.06
    еля
    -0.06
    POSITIVE LOGITS
    Türkiye
    0.06
    .dtd
    0.06
    zug
    0.06
    .keyCode
    0.06
     Armen
    0.06
    reater
    0.06
     Osmanlı
    0.06
    ntag
    0.06
     GÜ
    0.06
     SVC
    0.06
    Activations Density 0.038%

    No Known Activations