© 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
    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. 29991
    Prev
    Next
    INDEX
    Explanations

    XML code

    np_max-act · gemini-2.0-flash

    This neuron spotlights parts of XML namespace URIs (e.g. the “http://…,” domain fragments, and versioned path segments) inside xmlns attributes.

    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
     mosque
    -0.07
    {:
    -0.06
    .Fragment
    -0.06
     darkness
    -0.06
     ROC
    -0.06
    /mac
    -0.06
     panels
    -0.06
     Hass
    -0.06
    ]:↵
    -0.06
     dolaş
    -0.06
    POSITIVE LOGITS
     температу
    0.07
    addAction
    0.06
    _COLOR
    0.06
    Benefits
    0.06
    テル
    0.06
    _callback
    0.06
    引き
    0.06
    ýn
    0.06
    _Game
    0.06
     التاريخ
    0.06
    Activations Density 0.008%

    No Known Activations