© 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 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. 27-RESID-POST-AA
    11. 99727
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hair
    -0.06
     sits
    -0.06
    шт
    -0.06
    Ids
    -0.06
     matches
    -0.06
    Res
    -0.06
     managerial
    -0.06
     Б
    -0.06
    format
    -0.06
     Political
    -0.06
    POSITIVE LOGITS
     roli
    0.07
     наяв
    0.07
     엄마
    0.07
     nướng
    0.07
    emmel
    0.07
     dej
    0.07
     mutlu
    0.07
     özelliği
    0.06
     sám
    0.06
    setattr
    0.06
    Activations Density 0.037%

    No Known Activations