© 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. 127115
    Prev
    Next
    INDEX
    Explanations

    sys

    np_max-act · gemini-2.0-flash

    The neuron detects C/C++ include paths referencing system headers under a “sys/” directory (e.g. `<sys/socket.h>`, `<sys/types.h>`, `<sys/time.h>`, `<sys/select.h>`).

    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
    )didReceiveMemoryWarning
    -0.06
     火
    -0.06
     Ezra
    -0.06
    طف
    -0.06
    /all
    -0.06
    'Connor
    -0.06
    him
    -0.06
     yön
    -0.06
     sant
    -0.06
     Shade
    -0.06
    POSITIVE LOGITS
    declspec
    0.07
     报
    0.07
    inside
    0.07
     resize
    0.06
    ском
    0.06
    -loaded
    0.06
    -org
    0.06
    지노
    0.06
     nutritional
    0.06
    อส
    0.06
    Activations Density 0.001%

    No Known Activations