© 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. 41321
    Prev
    Next
    INDEX
    Explanations

    Myasthenia gravis

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the medical term “myasthenia gravis.”

    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
    _fire
    -0.06
    Clusters
    -0.06
     compatibility
    -0.06
     webhook
    -0.06
    _dispatch
    -0.06
    �
    -0.06
     رود
    -0.06
     삶
    -0.06
    ματος
    -0.06
    Streams
    -0.05
    POSITIVE LOGITS
    992
    0.07
    -thirds
    0.07
     �
    0.06
    -overlay
    0.06
     nutné
    0.06
     працівників
    0.06
     기능
    0.06
    -scale
    0.06
     dikke
    0.06
    EPS
    0.06
    Activations Density 0.001%

    No Known Activations