© 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. 109152
    Prev
    Next
    INDEX
    Explanations

    US locations

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on geographic place names—especially U.S. locations (states, cities) and institution names.

    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
     июля
    -0.07
     juegos
    -0.06
     Radio
    -0.06
     peaceful
    -0.06
     ripple
    -0.06
    _suspend
    -0.06
     Helpers
    -0.06
     Living
    -0.06
     Jamal
    -0.06
     Tele
    -0.06
    POSITIVE LOGITS
    .Then
    0.07
     كيف
    0.07
    nels
    0.07
    ogan
    0.06
     thủ
    0.06
    .ToInt
    0.06
    Hostname
    0.06
     sice
    0.06
    атки
    0.06
    inyin
    0.06
    Activations Density 0.029%

    No Known Activations