© 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. 3-RESID-POST-AA
    11. 123370
    Prev
    Next
    INDEX
    Explanations

    _user

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rotterdam
    -0.07
    /qt
    -0.06
     Ankara
    -0.06
    An
    -0.06
     Rodney
    -0.06
    
    -0.06
    立
    -0.06
    .SE
    -0.06
    標
    -0.06
    Ind
    -0.06
    POSITIVE LOGITS
    _user
    0.34
    _superuser
    0.08
    _DENIED
    0.07
    ุล
    0.07
     consumer
    0.07
    izen
    0.07
    user
    0.06
    withstanding
    0.06
    _task
    0.06
     minced
    0.06
    Activations Density 0.001%

    No Known Activations