© 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. 44986
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    The neuron activates on C/C++ linkage specification markers—namely the `extern "C"` block declarations.

    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
     neighbors
    -0.07
    694
    -0.07
    INF
    -0.06
     McC
    -0.06
    edian
    -0.06
    ROM
    -0.06
     donors
    -0.06
    ('%
    -0.06
     neighbours
    -0.06
     carne
    -0.06
    POSITIVE LOGITS
     removes
    0.07
     χρησιμοποι
    0.07
     багатьох
    0.07
     пля
    0.07
     folly
    0.07
    .system
    0.06
    *>(&
    0.06
     taxing
    0.06
     �
    0.06
    ざ
    0.06
    Activations Density 0.000%

    No Known Activations