© 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. 106938
    Prev
    Next
    INDEX
    Explanations

    f

    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
     имп
    -0.06
    ност
    -0.06
     yı
    -0.06
     persona
    -0.06
     getService
    -0.06
     goodies
    -0.06
     guru
    -0.06
     Madonna
    -0.06
    nya
    -0.06
    uvo
    -0.06
    POSITIVE LOGITS
     Peace
    0.07
     heritage
    0.07
     Applies
    0.06
     apply
    0.06
     Pay
    0.06
    _sheet
    0.06
    apply
    0.06
     еп
    0.06
     createDate
    0.06
     перв
    0.06
    Activations Density 0.001%

    No Known Activations