© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109324
    Prev
    Next
    INDEX
    Explanations

    medical tests

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on clinical test and dosage mentions—numbers, units, and test names (e.g. “1 mg oral dexamethasone suppression test,” “low-dose,” “OGTT,” etc.).

    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
    そう
    -0.07
    subtotal
    -0.07
    edException
    -0.07
     一般
    -0.06
    ác
    -0.06
     Jur
    -0.06
    297
    -0.06
    Я
    -0.06
     червня
    -0.06
    К
    -0.06
    POSITIVE LOGITS
     diagnose
    0.08
     lease
    0.06
     deceased
    0.06
     lname
    0.06
    _action
    0.06
    _colour
    0.06
     Pharma
    0.06
     erm
    0.06
     Telecom
    0.06
     Extreme
    0.06
    Activations Density 0.134%

    No Known Activations