© 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. 7714
    Prev
    Next
    INDEX
    Explanations

    illin

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of β-lactam antibiotics, especially drug names ending in “-cillin.”

    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
    оды
    -0.07
     prior
    -0.06
     pathlib
    -0.06
    enties
    -0.06
     eof
    -0.06
    	sc
    -0.06
    ularity
    -0.06
    ΑΡ
    -0.06
     одне
    -0.06
    xFC
    -0.06
    POSITIVE LOGITS
     pencil
    0.07
    uffles
    0.07
    still
    0.07
     XII
    0.07
    											
    0.07
     McKenzie
    0.07
     inspections
    0.07
    日本
    0.06
    _AXIS
    0.06
    ilenames
    0.06
    Activations Density 0.001%

    No Known Activations