© 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. 11900
    Prev
    Next
    INDEX
    Explanations

    say according

    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
     phys
    -0.06
     завтра
    -0.06
    ,↵
    -0.06
     ais
    -0.06
    ]})↵
    -0.06
     assured
    -0.06
     FINAL
    -0.06
     corrupt
    -0.06
     FOOD
    -0.06
     walls
    -0.06
    POSITIVE LOGITS
    nce
    0.07
    ileges
    0.06
     dan
    0.06
    eping
    0.06
    =>
    0.06
    orea
    0.06
     ok
    0.06
    ỹ
    0.06
     NSArray
    0.06
    estone
    0.06
    Activations Density 0.061%

    No Known Activations