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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6364
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron detects XML namespace declaration attributes (the “xmlns:” lines) in layout files.

    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
    .mkdirs
    -0.07
    ิบ
    -0.07
     дан
    -0.06
     pir
    -0.06
    /{}/
    -0.06
    兴
    -0.06
    ;background
    -0.06
    bian
    -0.06
     bilgisayar
    -0.06
     był
    -0.06
    POSITIVE LOGITS
    اهر
    0.07
    ξε
    0.06
    844
    0.06
     기억
    0.06
    Enums
    0.06
    Installer
    0.06
     MSI
    0.06
     você
    0.06
     changed
    0.06
     pode
    0.06
    Activations Density 0.001%

    No Known Activations