© 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. 9273
    Prev
    Next
    INDEX
    Explanations

    Java annotations code

    np_max-act · gemini-2.0-flash

    annotations related to software licensing and documentation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects Java annotation‐related constructs (e.g. ElementType, Retention, Target, Documented) in source code.

    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
    Filters
    -0.07
     advisory
    -0.07
    backup
    -0.06
     inserts
    -0.06
    Written
    -0.06
    sol
    -0.06
    ineTransform
    -0.06
    For
    -0.06
    lerden
    -0.06
     sentinel
    -0.06
    POSITIVE LOGITS
     дух
    0.07
     Termin
    0.07
    تم
    0.07
    وا
    0.06
     ưu
    0.06
    .rem
    0.06
     Durham
    0.06
     الول
    0.06
     Ads
    0.06
    Placement
    0.06
    Activations Density 0.001%

    No Known Activations