© 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. 7-RESID-POST-AA
    11. 22793
    Prev
    Next
    INDEX
    Explanations

    accent

    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
     hizo
    -0.07
     venues
    -0.06
    ?>"></
    -0.06
    <Void
    -0.06
    Tuy
    -0.06
     ange
    -0.06
     ())
    -0.06
    GENER
    -0.06
    _Global
    -0.06
    )):
    -0.06
    POSITIVE LOGITS
    _already
    0.06
     PictureBox
    0.06
     sınav
    0.06
    象
    0.06
     CallingConvention
    0.05
     thắng
    0.05
    <GameObject
    0.05
    ΑΙ
    0.05
    .Abstract
    0.05
    �
    0.05
    Activations Density 0.835%

    No Known Activations