Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 1248
    Prev
    Next
    INDEX
    Explanations

    Binding

    np_max-act · gemini-2.0-flash

    The neuron activates on XAML data-binding expressions (i.e. occurrences of the “Binding” markup extension and related binding syntax).

    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
    .MouseDown
    -0.07
    ержав
    -0.07
    automation
    -0.07
    (on
    -0.06
     similarities
    -0.06
     customization
    -0.06
    程
    -0.06
    (spell
    -0.06
     Hour
    -0.06
    кра
    -0.06
    POSITIVE LOGITS
     žid
    0.07
     бур
    0.07
     مدير
    0.06
    ũi
    0.06
     Bou
    0.06
     registry
    0.06
    Outlet
    0.06
     cogn
    0.06
     firing
    0.06
     gly
    0.06
    Activations Density 0.001%

    No Known Activations