© 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. 68322
    Prev
    Next
    INDEX
    Explanations

    creative professions

    np_max-act · gemini-2.0-flash

    The neuron activates on words naming people’s occupations, professions, or roles (e.g. “actor,” “player,” “inventor,” “mayor”).

    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
    -danger
    -0.07
    pesan
    -0.07
     moderators
    -0.07
    _RW
    -0.07
    cadena
    -0.07
    _PAY
    -0.07
     Bunlar
    -0.06
     때문에
    -0.06
     yêu
    -0.06
    JSImport
    -0.06
    POSITIVE LOGITS
     Olymp
    0.07
     Alabama
    0.07
    pyx
    0.07
     ch
    0.06
    interpre
    0.06
     curiosity
    0.06
     physicist
    0.06
    .species
    0.06
    .disable
    0.06
     Sophia
    0.06
    Activations Density 0.013%

    No Known Activations