© 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. 38514
    Prev
    Next
    INDEX
    Explanations

    Row

    np_max-act · gemini-2.0-flash

    This neuron detects VBA references to iterating over or determining the last row in a sheet (e.g. “Rows.Count,” “End(xlUp),” and row/lastRow variables).

    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
    ==='
    -0.07
    [['
    -0.07
    .echo
    -0.06
     sex
    -0.06
    .lastname
    -0.06
    _noise
    -0.06
    cookies
    -0.06
    nesia
    -0.06
    .toString
    -0.06
    ----------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
     الوط
    0.06
    дать
    0.06
     Elevated
    0.06
     componentDidMount
    0.06
     культуры
    0.06
     اروپ
    0.06
    σφα
    0.06
    ίδα
    0.05
     Một
    0.05
    děpodob
    0.05
    Activations Density 0.005%

    No Known Activations