© 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 EvalsExportsinterp-engineNEWAPI 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. 57880
    Prev
    Next
    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash

    The neuron is keyed to tokens that denote calendar dates (e.g. day/month names and numbers).

    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
     Kepler
    -0.07
     Lightweight
    -0.07
     двор
    -0.07
    slope
    -0.06
     epoll
    -0.06
     thuế
    -0.06
    ellij
    -0.06
     Martian
    -0.06
     бл
    -0.06
     userdata
    -0.06
    POSITIVE LOGITS
     arranging
    0.07
     Subscriber
    0.06
     getCurrent
    0.06
    >'↵
    0.06
     disruptions
    0.06
    igest
    0.06
    imos
    0.06
     subscriber
    0.06
    ulatory
    0.06
     Nikon
    0.06
    Activations Density 0.132%

    No Known Activations