© 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. 7-RESID-POST-AA
    11. 71450
    Prev
    Next
    INDEX
    Explanations

    I

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /templates
    -0.07
     giorni
    -0.07
    ween
    -0.07
     sy
    -0.06
     brush
    -0.06
     Hoy
    -0.06
     Had
    -0.06
    >Show
    -0.06
     summarized
    -0.06
     Pais
    -0.06
    POSITIVE LOGITS
    лян
    0.07
    Update
    0.06
    (jQuery
    0.06
    ownt
    0.06
     quy
    0.06
    \db
    0.06
    arlar
    0.06
     шк
    0.06
    хи
    0.06
    grim
    0.06
    Activations Density 0.011%

    No Known Activations