© 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. 38546
    Prev
    Next
    INDEX
    Explanations

    anecdotes

    np_max-act · gemini-2.0-flash

    This neuron identifies informal gendered terms referring to women or girls (e.g. “girl,” “gal,” “lady”).

    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
    宣
    -0.07
     pitfalls
    -0.06
    産
    -0.06
     border
    -0.06
    ZIP
    -0.06
     Furniture
    -0.06
    HP
    -0.06
    ementia
    -0.06
    400
    -0.06
    Equals
    -0.06
    POSITIVE LOGITS
    ->_
    0.07
     allot
    0.07
    ()->
    0.07
     чемпион
    0.06
     příležit
    0.06
     deliber
    0.06
    ٫
    0.06
     -.
    0.06
     Asi
    0.06
     olarak
    0.06
    Activations Density 0.068%

    No Known Activations