© 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. 73863
    Prev
    Next
    INDEX
    Explanations

    hyperalgesia and inflammation

    np_max-act · gemini-2.0-flash

    This neuron detects subword fragments of technical biomedical terms that denote heightened or abnormal physiological responses—e.g. “hyper-,” “algesia,” “allodynia,” “responsiveness,” or “ongoing activity.”

    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
    Foundation
    -0.06
     한
    -0.06
    ]byte
    -0.06
    ��
    -0.06
    ByteArray
    -0.06
    launcher
    -0.06
    월부터
    -0.06
    Dim
    -0.06
     unto
    -0.06
    imeInterval
    -0.06
    POSITIVE LOGITS
     mapped
    0.07
     ),
    ↵
    0.06
     currency
    0.06
    xdc
    0.06
     undo
    0.06
     liberties
    0.06
     جستارهای
    0.06
    ?>"><?
    0.06
     outbound
    0.06
    VIDEO
    0.06
    Activations Density 0.007%

    No Known Activations