© 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. 19-RESID-POST-AA
    11. 112312
    Prev
    Next
    INDEX
    Explanations

    chocolate

    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
    -unused
    -0.07
    PDO
    -0.07
     RestClient
    -0.07
    -bedroom
    -0.06
     LNG
    -0.06
    DataProvider
    -0.06
     QSql
    -0.06
    eygamber
    -0.06
    iq
    -0.06
    上げ
    -0.06
    POSITIVE LOGITS
    chat
    0.07
     
    0.07
     chocolates
    0.07
     cocoa
    0.07
     chocol
    0.07
     Chocolate
    0.07
     kW
    0.07
     chocolate
    0.07
     重
    0.07
    .Chat
    0.07
    Activations Density 0.003%

    No Known Activations