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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56764
    Prev
    Next
    INDEX
    Explanations

    complex

    np_max-act · gemini-2.0-flash

    This neuron activates on substrings of specialized geometry terms (e.g. Calabi-Yau, Lagrangian) found in advanced mathematical terminology.

    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
    /mark
    -0.07
    .Marshal
    -0.07
     scratched
    -0.07
    syscall
    -0.06
    /gin
    -0.06
    =search
    -0.06
    (Common
    -0.06
     практически
    -0.06
    ::::/
    -0.06
     Teeth
    -0.06
    POSITIVE LOGITS
    载
    0.07
     نقل
    0.07
    _RECEIVED
    0.06
     svens
    0.06
     #↵
    0.06
     liber
    0.06
     reflective
    0.06
     woodworking
    0.06
    HIP
    0.06
     이미지
    0.06
    Activations Density 0.003%

    No Known Activations