© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13518
    Prev
    Next
    INDEX
    Explanations

    business/retail

    np_max-act · gemini-2.0-flash

    The neuron activates on section‐header labels in clinical notes—especially operative report headings like “SURGEON:” or “PERFORMED:”.

    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
     kvp
    -0.07
     Freeman
    -0.07
     밝
    -0.06
    asis
    -0.06
    atar
    -0.06
    filePath
    -0.06
    precedented
    -0.06
    ya
    -0.06
     Educational
    -0.06
    raith
    -0.06
    POSITIVE LOGITS
     última
    0.07
    ”—
    0.06
     invited
    0.06
     enlisted
    0.06
    _REMOVE
    0.06
     ),↵↵
    0.06
    })"↵
    0.06
    ↵
    0.06
     facilities
    0.06
    同时
    0.06
    Activations Density 0.029%

    No Known Activations