© 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
    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. 130010
    Prev
    Next
    INDEX
    Explanations

    VC

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of Microsoft’s Visual C/C++ compiler (e.g. “MS”, “VC”, “Visual”, “C++” and related version tokens).

    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
    teenth
    -0.06
    Ik
    -0.06
    odafone
    -0.06
    ğan
    -0.06
    cház
    -0.06
    ẳng
    -0.06
    ategor
    -0.06
    STITUTE
    -0.06
    十
    -0.06
    ainer
    -0.06
    POSITIVE LOGITS
    getImage
    0.07
     использ
    0.07
     itemId
    0.07
    methodName
    0.07
    .context
    0.07
     charset
    0.06
     Collapse
    0.06
     creds
    0.06
     setObject
    0.06
    (void
    0.06
    Activations Density 0.004%

    No Known Activations