© 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. 6009
    Prev
    Next
    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash

    This neuron detects copyright notices in code comments (e.g. “Copyright (C …)”).

    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
     τελ
    -0.06
    _dt
    -0.06
    nk
    -0.06
     Erotic
    -0.06
    ưở
    -0.06
    ประเภท
    -0.06
     lưới
    -0.06
    .notice
    -0.06
    INIT
    -0.06
     oa
    -0.06
    POSITIVE LOGITS
    =n
    0.07
     Northwestern
    0.07
    -machine
    0.06
    нав
    0.06
    Workspace
    0.06
     Casinos
    0.06
     Tarif
    0.06
    ностью
    0.06
    .Collapsed
    0.06
    _Space
    0.06
    Activations Density 0.001%

    No Known Activations