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

    Neuronpedia

    Jacobian LensNEW
    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. 38711
    Prev
    Next
    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash

    This neuron detects C/C++ macro invocations that define Linux ioctl commands (e.g. those using _IO, _IOR, _IOW, 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
    GPL
    -0.07
     visions
    -0.06
    谢
    -0.06
     Jest
    -0.06
    adece
    -0.06
    Suit
    -0.06
     analog
    -0.06
    crest
    -0.06
     formats
    -0.06
     मद
    -0.06
    POSITIVE LOGITS
     іншого
    0.07
     لإ
    0.07
    ticks
    0.06
    력이
    0.06
    bial
    0.06
     заболевания
    0.06
     someone
    0.06
     �
    0.06
     The
    0.06
     الام
    0.06
    Activations Density 0.005%

    No Known Activations