© 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 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. 45152
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    code snippets and programming concepts related to user interface elements and data binding.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on XML-style UI markup, spotting layout element tags and their attribute names (e.g. Xamarin.Forms XAML elements and properties).

    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
    Override
    -0.07
     lasers
    -0.07
     disturb
    -0.07
    approx
    -0.07
    live
    -0.06
     breach
    -0.06
    employment
    -0.06
    playing
    -0.06
     change
    -0.06
     targeted
    -0.06
    POSITIVE LOGITS
     편
    0.08
    'être
    0.07
    іє
    0.07
     Є
    0.06
     �
    0.06
     Η
    0.06
     ("/
    0.06
    Baş
    0.06
    undry
    0.06
    ऊ
    0.06
    Activations Density 0.127%

    No Known Activations