© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59097
    Prev
    Next
    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “test” and related testing terms (e.g. “unit,” “testing,” “test,” “tests”).

    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
    Instagram
    -0.07
    Mas
    -0.06
     image
    -0.06
    Bot
    -0.06
     cơm
    -0.06
     /*!<
    -0.06
    Sel
    -0.06
    Fetch
    -0.06
     Comparator
    -0.06
    ();//
    -0.06
    POSITIVE LOGITS
     desarroll
    0.07
    ورات
    0.07
    diamond
    0.07
    'autres
    0.07
     přístup
    0.07
     května
    0.07
    чески
    0.07
     publi
    0.07
    ρωση
    0.07
     drž
    0.07
    Activations Density 0.018%

    No Known Activations