© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30635
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash

    This neuron detects formal academic discourse markers and phrasing typical of research-paper abstracts and introductions (e.g. “has been,” “have recently,” “proposed,” “demonstrated”).

    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
     △
    -0.07
    Markers
    -0.07
     fotograf
    -0.06
    (rect
    -0.06
    xEA
    -0.06
    LayoutPanel
    -0.06
     dosud
    -0.06
     Deleted
    -0.06
    getFile
    -0.06
     अल
    -0.06
    POSITIVE LOGITS
     Naval
    0.07
     Terry
    0.06
    Trading
    0.06
     Oscar
    0.06
    计算
    0.06
    Ú
    0.06
    _argv
    0.06
    )object
    0.06
     Wrapper
    0.06
    Nic
    0.06
    Activations Density 0.125%

    No Known Activations