© 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. 11-RESID-POST-AA
    11. 41638
    Prev
    Next
    INDEX
    Explanations

    geographical areas

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens describing geographical boundaries or borders (e.g., “borders,” “to the north,” “to the east”).

    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
     thải
    -0.06
    >Hello
    -0.06
     उसन
    -0.06
     Height
    -0.06
    ucken
    -0.06
    关于
    -0.06
     Profiles
    -0.06
    ลงท
    -0.06
     Eigen
    -0.06
     romant
    -0.06
    POSITIVE LOGITS
     пласти
    0.06
     Arizona
    0.06
    anlı
    0.06
     второй
    0.06
     viagra
    0.06
     College
    0.06
     puppet
    0.06
    ocom
    0.06
    _Cancel
    0.06
     станов
    0.06
    Activations Density 0.008%

    No Known Activations