© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 57330
    Prev
    Next
    INDEX
    Explanations

    XML sequence tag

    np_max-act · gemini-2.0-flash

    The neuron detects XML Schema / structural XML markup (schema elements, tags and attributes) in documents.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الث
    -0.06
     inventory
    -0.06
     asset
    -0.06
     expresses
    -0.06
     VF
    -0.06
     starts
    -0.06
     plugins
    -0.06
    Times
    -0.06
    ُو
    -0.06
     heads
    -0.06
    POSITIVE LOGITS
     :↵↵↵↵
    0.07
     extra
    0.06
    !↵↵↵↵
    0.06
     århus
    0.06
     =↵↵
    0.06
     nord
    0.06
    北市
    0.06
    MenuBar
    0.06
    |RF
    0.06
     NUITKA
    0.06
    Activations Density 0.002%

    No Known Activations