© 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. 27-RESID-POST-AA
    11. 7244
    Prev
    Next
    INDEX
    Explanations

    quote

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uegos
    -0.07
     "
    -0.07
    ("
    -0.07
     august
    -0.07
    (agent
    -0.07
    (),"
    -0.07
     observable
    -0.07
    ANT
    -0.07
     Sensors
    -0.06
     Bayesian
    -0.06
    POSITIVE LOGITS
    >'.↵
    0.07
     Kimber
    0.07
    Bre
    0.07
    çi
    0.07
    .faceVertexUvs
    0.07
    長
    0.07
    .'↵
    0.07
    !'
    0.06
    ">'+↵
    0.06
     QUI
    0.06
    Activations Density 0.128%

    No Known Activations