© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110300
    Prev
    Next
    INDEX
    Explanations

    aspects of life

    np_max-act · gemini-2.0-flash

    The neuron activates on words naming institutional sectors or organizational domains (e.g., government, academia, industry, national security, etc.).

    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
    orient
    -0.07
    oken
    -0.06
     Azerbaijan
    -0.06
    STA
    -0.06
     MMC
    -0.06
    downloads
    -0.06
     št
    -0.06
    "For
    -0.06
    "To
    -0.06
     Task
    -0.06
    POSITIVE LOGITS
     electr
    0.08
     pulver
    0.08
     Fucking
    0.06
    ประถม
    0.06
     arbe
    0.06
     Know
    0.06
     个
    0.06
     Základní
    0.06
    cido
    0.06
     offer
    0.06
    Activations Density 0.082%

    No Known Activations