© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 124927
    Prev
    Next
    INDEX
    Explanations

    car brands

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of luxury automotive brand names (e.g., Maserati, Infiniti, Acura, Genesis).

    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
     Vancouver
    -0.07
    geois
    -0.06
     dinheiro
    -0.06
    izona
    -0.06
     wz
    -0.06
    шов
    -0.06
     bishops
    -0.06
     desert
    -0.06
    arendra
    -0.06
    %.↵↵
    -0.06
    POSITIVE LOGITS
    u
    0.07
    /pol
    0.06
     squ
    0.06
     &___
    0.06
    =B
    0.06
    :bold
    0.06
     nfl
    0.06
     letter
    0.06
     кал
    0.06
    quisite
    0.06
    Activations Density 0.011%

    No Known Activations