© 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. 11-RESID-POST-AA
    11. 46843
    Prev
    Next
    INDEX
    Explanations

    and

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANGE
    -0.06
     конструк
    -0.06
    ethe
    -0.06
    елення
    -0.06
    ALLY
    -0.06
    (search
    -0.06
     动
    -0.06
     short
    -0.06
    AAAA
    -0.06
    'al
    -0.06
    POSITIVE LOGITS
    .Window
    0.07
     Met
    0.07
    .commands
    0.07
     Developed
    0.07
    /windows
    0.07
    .UTF
    0.07
     Vander
    0.06
     UNS
    0.06
     Solomon
    0.06
    穴
    0.06
    Activations Density 0.039%

    No Known Activations