© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 126856
    Prev
    Next
    INDEX
    Explanations

    days of the week

    np_max-act · gemini-2.0-flash

    This neuron detects date‐header lines by spotting weekday names (e.g. “Wednesday,” “Tuesday,” “Sunday”).

    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
     운영
    -0.07
     poměrně
    -0.06
     approximate
    -0.06
     Acer
    -0.06
    	Function
    -0.06
    _activate
    -0.06
     fica
    -0.06
     спад
    -0.06
     випад
    -0.06
    root
    -0.06
    POSITIVE LOGITS
     Equal
    0.06
    $scope
    0.06
     imprison
    0.06
    ele
    0.06
     Income
    0.06
    ằ
    0.06
    ел
    0.06
    _CHARACTER
    0.06
     income
    0.06
    นาง
    0.06
    Activations Density 0.004%

    No Known Activations