© 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 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. 56602
    Prev
    Next
    INDEX
    Explanations

    filler text

    np_max-act · gemini-2.0-flash

    This neuron activates on Latin “Lorem ipsum”–style filler words used as dummy text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    Qed
    -0.07
    ussy
    -0.07
     airplanes
    -0.07
     partic
    -0.06
     predict
    -0.06
     Gordon
    -0.06
     planner
    -0.06
     melts
    -0.06
    иля
    -0.06
    від
    -0.06
    POSITIVE LOGITS
    ґ
    0.06
    Yahoo
    0.06
     revamped
    0.06
    .urlencoded
    0.06
     `-
    0.06
    ()):↵
    0.06
    یستم
    0.06
     biç
    0.06
    」，
    0.06
    -ob
    0.06
    Activations Density 0.003%

    No Known Activations