© 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 EvalsExportsinterp-engineNEWAPI 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. 57896
    Prev
    Next
    INDEX
    Explanations

    data types

    np_max-act · gemini-2.0-flash

    The neuron fires on C header‐file references—that is, tokens naming “.h” include files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    C/C++ preprocessor directives and includes for standard libraries.

    oai_token-act-pair · gpt-4o-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
    .tap
    -0.07
    WhatsApp
    -0.07
    	code
    -0.06
     coloured
    -0.06
    ává
    -0.06
     BTS
    -0.06
    σκεται
    -0.06
     zayıf
    -0.06
     Modelo
    -0.06
     tion
    -0.06
    POSITIVE LOGITS
    .categories
    0.06
    uckle
    0.06
    ={{↵
    0.06
    저
    0.06
     ancestry
    0.06
     пож
    0.06
     боли
    0.06
     keeping
    0.06
     Patel
    0.06
    .offsetWidth
    0.06
    Activations Density 0.003%

    No Known Activations