© 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. 12445
    Prev
    Next
    INDEX
    Explanations

    medical treatments and disorders

    np_max-act · gemini-2.0-flash

    This neuron detects words that specify prolonged or chronic medical treatments or exposures (e.g. “chronic,” “long-term,” “preventive,” “supplementation”).

    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
     utilities
    -0.07
    Early
    -0.07
    ثمان
    -0.07
     فقط
    -0.07
    ерше
    -0.07
     universal
    -0.07
    _map
    -0.06
     инструмент
    -0.06
    List
    -0.06
     πρώτη
    -0.06
    POSITIVE LOGITS
     longtime
    0.07
    ifu
    0.06
     dopad
    0.06
     dlouhodob
    0.06
     неиз
    0.06
     alo
    0.06
    getJSON
    0.06
     regularization
    0.06
    otos
    0.06
    售
    0.06
    Activations Density 0.067%

    No Known Activations