© 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. 57605
    Prev
    Next
    INDEX
    Explanations

    Settings

    np_max-act · gemini-2.0-flash

    This neuron fires on the “Settings” element names in XML configuration files, especially within `<configSections>` and `<applicationSettings>` blocks.

    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
     Spare
    -0.06
    EMU
    -0.06
     угод
    -0.06
     birth
    -0.06
    �
    -0.06
     bụi
    -0.06
    زيز
    -0.06
    ():
↵
    -0.06
    .SH
    -0.06
    روز
    -0.06
    POSITIVE LOGITS
     orthodox
    0.07
     Covent
    0.06
    _FIELD
    0.06
     SO
    0.06
    _field
    0.06
     labeled
    0.06
     Postal
    0.06
     코
    0.06
     xlabel
    0.06
     şu
    0.06
    Activations Density 0.002%

    No Known Activations