© 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. 58602
    Prev
    Next
    INDEX
    Explanations

    Rails

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of the Ruby on Rails framework (e.g. “Rails” or “Ruby on Rails”).

    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
     변수
    -0.06
     phase
    -0.06
     edt
    -0.06
    νονται
    -0.06
    undan
    -0.06
    _ptrs
    -0.06
    419
    -0.06
     fishes
    -0.06
     Circuit
    -0.06
     شیمی
    -0.06
    POSITIVE LOGITS
     Rails
    0.08
     норматив
    0.08
    _bias
    0.08
     Salesforce
    0.07
    Rails
    0.07
     Nichols
    0.07
     CBS
    0.07
    -object
    0.06
     addslashes
    0.06
    _rpc
    0.06
    Activations Density 0.007%

    No Known Activations