© 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. 58221
    Prev
    Next
    INDEX
    Explanations

    CURLOPT

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of cURL’s CURLOPT constants—that is, when the code is setting cURL options.

    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
     producers
    -0.07
    Host
    -0.07
     fen
    -0.07
    奥
    -0.06
    iểu
    -0.06
     đặc
    -0.06
     Ef
    -0.06
     diffé
    -0.06
    Ef
    -0.06
     vm
    -0.06
    POSITIVE LOGITS
     CURLOPT
    0.14
    URLOPT
    0.09
     different
    0.07
     ersten
    0.07
    (Calendar
    0.07
     __("
    0.07
    (plot
    0.06
    ращ
    0.06
     taken
    0.06
    etzt
    0.06
    Activations Density 0.000%

    No Known Activations