© 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. 58215
    Prev
    Next
    INDEX
    Explanations

    tikz code

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numeric literals (e.g. floating‐point numbers used for coordinates or measurements).

    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
     zf
    -0.06
     kontro
    -0.06
    فال
    -0.06
    .details
    -0.06
     tý
    -0.06
     وضع
    -0.06
    Liv
    -0.06
    opro
    -0.06
     continuation
    -0.05
    Evento
    -0.05
    POSITIVE LOGITS
    作用
    0.06
    (text
    0.06
    QPCP
    0.06
    ;",↵
    0.06
     广
    0.06
    Pressed
    0.06
     stolen
    0.06
     historian
    0.06
     recommendations
    0.06
     setInput
    0.06
    Activations Density 0.005%

    No Known Activations