© 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. 127130
    Prev
    Next
    INDEX
    Explanations

    servlet

    np_max-act · gemini-2.0-flash

    This neuron activates on XML elements related to servlet and filter declarations (e.g. <servlet>, <servlet-mapping>, and <filter> tags) in a web application config.

    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
     AD
    -0.07
    alar
    -0.06
     anz
    -0.06
     dr
    -0.06
     Max
    -0.06
     invade
    -0.06
    X
    -0.06
     TY
    -0.06
     подраз
    -0.06
     Lear
    -0.06
    POSITIVE LOGITS
     servlet
    0.12
    Servlet
    0.12
     Servlet
    0.12
    .servlet
    0.12
    ervlet
    0.10
    .Servlet
    0.08
     ServletException
    0.08
    Qt
    0.08
    .slice
    0.07
     HttpServletResponse
    0.07
    Activations Density 0.002%

    No Known Activations