© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68445
    Prev
    Next
    INDEX
    Explanations

    conservative

    np_max-act · gemini-2.0-flash

    This neuron responds to words naming medical treatments or management approaches (e.g., conservative treatment, follow-up, surgery).

    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
    узы
    -0.07
    except
    -0.07
     SignIn
    -0.06
    	Code
    -0.06
     follic
    -0.06
    finance
    -0.06
    Report
    -0.06
     kostenlos
    -0.06
     tweet
    -0.06
    eeper
    -0.06
    POSITIVE LOGITS
    �
    0.07
     активно
    0.07
    _RESERVED
    0.06
    ountries
    0.06
    ائلة
    0.06
     ανά
    0.06
    ]{
    0.06
    ibilidade
    0.06
    -meta
    0.06
    .micro
    0.06
    Activations Density 0.019%

    No Known Activations