© 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. 53420
    Prev
    Next
    INDEX
    Explanations

    code/math/exceptions

    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
    やって
    -0.07
    霊
    -0.07
    鹿
    -0.07
    Routine
    -0.07
     force
    -0.06
    askell
    -0.06
    الة
    -0.06
     판매
    -0.06
    :test
    -0.06
     distinguish
    -0.06
    POSITIVE LOGITS
     "+↵
    0.06
     russ
    0.06
    /cop
    0.06
    xima
    0.06
     migraine
    0.06
    ecko
    0.06
    Neighbor
    0.06
    _CORE
    0.06
    _dbg
    0.06
     Runner
    0.06
    Activations Density 0.000%

    No Known Activations