© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125105
    Prev
    Next
    INDEX
    Explanations

    xsd

    np_max-act · gemini-2.0-flash

    The neuron detects XML Schema constructs, especially elements and attributes using the “xsd:” prefix.

    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
     pow
    -0.06
    oncé
    -0.06
    .cell
    -0.06
    Cache
    -0.06
    다고
    -0.06
    .debug
    -0.06
    .Label
    -0.06
    ░
    -0.06
     adventurous
    -0.05
    912
    -0.05
    POSITIVE LOGITS
    xsd
    0.09
    рд
    0.07
     pierws
    0.07
    	Scanner
    0.07
    dx
    0.07
    },
    0.07
    (xs
    0.07
     exce
    0.07
     Перв
    0.06
     přes
    0.06
    Activations Density 0.001%

    No Known Activations