© 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. 9152
    Prev
    Next
    INDEX
    Explanations

    medical terminology

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on substrings of the word “bronchoconstriction” (and variants), thus detecting mentions of airway constriction.

    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
    gregated
    -0.07
    Father
    -0.06
     gió
    -0.06
     facet
    -0.06
     maior
    -0.06
    _DC
    -0.06
    medium
    -0.06
     görün
    -0.06
     městě
    -0.06
    他们
    -0.06
    POSITIVE LOGITS
    .json
    0.07
     동
    0.07
    	token
    0.06
    SERVER
    0.06
    visa
    0.06
     tsunami
    0.06
    MQ
    0.06
    fee
    0.06
    @Override
    0.06
    (role
    0.06
    Activations Density 0.068%

    No Known Activations