© 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 EvalsExportsinterp-engineNEWAPI 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. 58991
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on common stop‐words (frequently used short words like “better,” “shouldn’t,” “doesn’t,” “hasn’t,” etc.).

    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
     s
    -0.06
     saya
    -0.06
    Mem
    -0.06
     tr
    -0.06
     Lawyers
    -0.06
     subsequ
    -0.06
    formula
    -0.06
    |.
    -0.06
    /xml
    -0.06
    GUID
    -0.06
    POSITIVE LOGITS
    寶
    0.08
     acct
    0.07
    elry
    0.06
    munition
    0.06
     spectacle
    0.06
     fres
    0.06
     versa
    0.06
    ưới
    0.06
    Honda
    0.06
    hip
    0.06
    Activations Density 0.022%

    No Known Activations