© 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. 19-RESID-POST-AA
    11. 84594
    Prev
    Next
    INDEX
    Explanations

    in

    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
     stress
    -0.07
    ENTICATION
    -0.07
    Arrow
    -0.07
     creativity
    -0.06
     Forever
    -0.06
     emiss
    -0.06
     pressure
    -0.06
    asting
    -0.06
    Against
    -0.06
    -script
    -0.06
    POSITIVE LOGITS
     isIn
    0.07
     百度收录
    0.07
     \<^
    0.06
    (ep
    0.06
    �n
    0.06
     Palm
    0.06
     LoginForm
    0.06
     intf
    0.06
     Ün
    0.06
    axon
    0.06
    Activations Density 0.001%

    No Known Activations