© 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. 58025
    Prev
    Next
    INDEX
    Explanations

    US

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens with decimal points (floating-point numbers).

    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
     Cathedral
    -0.08
    characters
    -0.07
     lifestyle
    -0.07
    Smith
    -0.07
     bol
    -0.06
     Buddhist
    -0.06
     deposit
    -0.06
    菌
    -0.06
     animation
    -0.06
     adjustment
    -0.06
    POSITIVE LOGITS
    /testify
    0.06
     застосов
    0.06
    ่ก
    0.06
    _CRC
    0.06
     рішення
    0.06
     CPPUNIT
    0.06
    YTE
    0.06
    =_('
    0.06
    .setSize
    0.06
    '),'
    0.06
    Activations Density 0.231%

    No Known Activations