© 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. 7683
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron detects the abbreviated Federal Reporter appellate‐procedure citation pattern (e.g. “Fed. R. App. P.” and its punctuation).

    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
    ۱
    -0.07
     Fay
    -0.07
    cname
    -0.07
    TMP
    -0.06
     некотор
    -0.06
    etine
    -0.06
    488
    -0.06
     непри
    -0.06
     Pfizer
    -0.06
    πα
    -0.06
    POSITIVE LOGITS
     leakage
    0.06
     EMAIL
    0.06
     Happ
    0.06
     parliament
    0.06
     elev
    0.06
    /as
    0.06
     môn
    0.06
     Params
    0.06
     handful
    0.06
     movimiento
    0.06
    Activations Density 0.001%

    No Known Activations