© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 85428
    Prev
    Next
    INDEX
    Explanations

    actions and instructions related to software operation or configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ewe
    -0.07
    dej
    -0.06
     controversial
    -0.06
    ubat
    -0.06
    rega
    -0.06
    alli
    -0.06
    oola
    -0.06
    ghi
    -0.06
     Binder
    -0.06
    altet
    -0.06
    POSITIVE LOGITS
    auss
    0.06
    .accel
    0.06
     MainWindow
    0.06
    _Cmd
    0.06
     BÄĽ
    0.06
     comando
    0.06
    mainwindow
    0.06
    ÏģÏį
    0.06
     obed
    0.06
    yms
    0.06
    Activations Density 0.017%

    No Known Activations