© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27752
    Prev
    Next
    INDEX
    Explanations

    cock/dick

    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
     Walters
    -0.07
     naprost
    -0.06
     Keeping
    -0.06
    Dirs
    -0.06
    mland
    -0.06
     Μα
    -0.06
    šetř
    -0.06
    (email
    -0.06
    过程
    -0.06
    rava
    -0.06
    POSITIVE LOGITS
     áll
    0.07
     needle
    0.06
     ал
    0.06
     dicks
    0.06
    swire
    0.06
    (rate
    0.06
     penis
    0.06
    NavController
    0.06
     Titanic
    0.06
    =localhost
    0.06
    Activations Density 0.013%

    No Known Activations