© 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
    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. 7128
    Prev
    Next
    INDEX
    Explanations

    ::

    np_max-act · gemini-2.0-flash

    This neuron activates on C++ scope‐resolution patterns—namely tokens like “::” and namespace qualifiers (e.g. “std::”).

    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
     Operator
    -0.07
    (encoder
    -0.06
    .datab
    -0.06
    ="[
    -0.06
    Expansion
    -0.06
     unseren
    -0.06
    殖
    -0.06
    .reducer
    -0.06
    Recursive
    -0.06
    .send
    -0.06
    POSITIVE LOGITS
     руками
    0.07
     drifting
    0.06
    -origin
    0.06
     fingertips
    0.06
     Chile
    0.06
     relocate
    0.06
    สหร
    0.06
     GPLv
    0.06
    encodeURIComponent
    0.06
     falsely
    0.06
    Activations Density 0.001%

    No Known Activations