© 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 EvalsExportsinterp-engineNEWAPI 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. 34002
    Prev
    Next
    INDEX
    Explanations

    Only

    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
    üns
    -0.07
     quảng
    -0.07
     dương
    -0.06
    <M
    -0.06
    λογία
    -0.06
    ่าต
    -0.06
    mmm
    -0.06
     external
    -0.06
    لام
    -0.06
     Padding
    -0.06
    POSITIVE LOGITS
     ister
    0.08
    dou
    0.08
     reserved
    0.07
     seizure
    0.06
     асп
    0.06
     contar
    0.06
     exquisite
    0.06
    (elements
    0.06
    izando
    0.06
     Harry
    0.06
    Activations Density 0.002%

    No Known Activations