© 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. 56879
    Prev
    Next
    INDEX
    Explanations

    User

    np_max-act · gemini-2.0-flash

    This neuron detects UI‐style field or label tokens (e.g. “User:” or “input”) that mark metadata or menu elements.

    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
    cak
    -0.08
    ячи
    -0.07
    altar
    -0.07
    _window
    -0.07
    ΟΚ
    -0.07
    allon
    -0.07
     pink
    -0.06
    erialized
    -0.06
    Seven
    -0.06
    اهد
    -0.06
    POSITIVE LOGITS
     draggable
    0.07
     プ
    0.06
    GRID
    0.06
    _private
    0.06
     didnt
    0.06
    <li
    0.06
     Basis
    0.06
     stringWith
    0.06
    (dot
    0.06
    .ham
    0.06
    Activations Density 0.154%

    No Known Activations