© 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. 91302
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of professional sports team names (e.g. MLB franchises).

    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
    Arg
    -0.07
     maternal
    -0.07
    補
    -0.06
    ieve
    -0.06
     كام
    -0.06
    下载次数
    -0.06
    導
    -0.06
    oused
    -0.06
     sigue
    -0.06
     ARG
    -0.06
    POSITIVE LOGITS
    .Other
    0.07
     impressed
    0.06
    ODE
    0.06
    ‌اند
    0.06
    名稱
    0.06
     lille
    0.06
     functionalities
    0.06
    oti
    0.06
    ode
    0.06
     atd
    0.06
    Activations Density 0.009%

    No Known Activations