© 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. 89329
    Prev
    Next
    INDEX
    Explanations

    medical conditions and symptoms

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of medical treatment—especially section headings or phrases discussing how a condition is treated.

    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
     bullying
    -0.07
    endi
    -0.06
    _button
    -0.06
     station
    -0.06
    amera
    -0.06
    ungal
    -0.06
    Angular
    -0.06
    lok
    -0.06
     Kou
    -0.06
     ไป
    -0.06
    POSITIVE LOGITS
     (*
    0.06
     друж
    0.06
     )]↵
    0.06
    ージ
    0.06
     عفش
    0.06
     Constructor
    0.06
     основе
    0.06
     enquanto
    0.06
    (SYS
    0.06
     приз
    0.06
    Activations Density 0.043%

    No Known Activations