© 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. 124967
    Prev
    Next
    INDEX
    Explanations

    birth/death years

    np_max-act · gemini-2.0-flash

    This neuron identifies the numeric year token in category lines marking a person’s death year.

    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
     CreateMap
    -0.06
    TestClass
    -0.06
     SendMessage
    -0.06
    Incomplete
    -0.06
    (ship
    -0.06
     incomplete
    -0.06
    TURN
    -0.06
    (origin
    -0.06
    ắm
    -0.06
    uname
    -0.06
    POSITIVE LOGITS
     espacio
    0.08
     esp
    0.07
     Julia
    0.07
     Když
    0.07
     TripAdvisor
    0.06
     München
    0.06
     кварти
    0.06
    .client
    0.06
    +xml
    0.06
    анд
    0.06
    Activations Density 0.002%

    No Known Activations