© 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. 30558
    Prev
    Next
    INDEX
    Explanations

    oo

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the “odoo” XML root tag (i.e. the tokens “od” + “oo” forming `<odoo>`).

    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
     democrat
    -0.07
    Ô
    -0.06
    _courses
    -0.06
     мая
    -0.06
    (TRUE
    -0.06
    ORE
    -0.06
    inki
    -0.06
    茨
    -0.06
    reak
    -0.06
     glean
    -0.06
    POSITIVE LOGITS
     ΑΠ
    0.07
     Albuquerque
    0.07
     požad
    0.06
    jsonwebtoken
    0.06
     Sm
    0.06
    /B
    0.06
     LOCAL
    0.06
     Τα
    0.06
     Farm
    0.06
    riterion
    0.06
    Activations Density 0.006%

    No Known Activations