© 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. 91627
    Prev
    Next
    INDEX
    Explanations

    myeloperoxidase and hydrangeas

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of the enzyme myeloperoxidase (i.e. “peroxidase” or MPO) in the text.

    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
    elems
    -0.07
     acet
    -0.06
     Intl
    -0.06
     Něk
    -0.06
     cables
    -0.06
     Arap
    -0.06
    _angles
    -0.06
     protocols
    -0.06
     Currently
    -0.06
     очі
    -0.06
    POSITIVE LOGITS
    ees
    0.07
    published
    0.06
    (usuario
    0.06
     конкрет
    0.06
     muddy
    0.06
     образования
    0.06
    جی
    0.06
    íc
    0.06
    λικά
    0.06
    udic
    0.06
    Activations Density 0.000%

    No Known Activations