© 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. 119206
    Prev
    Next
    INDEX
    Explanations

    terms related to signal processing and sampling in data analysis

    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
     Kraj
    -0.08
    anggal
    -0.07
    ycz
    -0.06
     Vall
    -0.06
    ÙĨÙĪÛĮس
    -0.06
    Multiplicity
    -0.06
    ÄĽÅ¾
    -0.06
     quota
    -0.06
     Trace
    -0.06
    ospace
    -0.06
    POSITIVE LOGITS
     Slide
    0.08
     sliding
    0.08
     windows
    0.08
    rolling
    0.08
     window
    0.08
    -window
    0.08
    WindowSize
    0.08
     WINDOW
    0.07
    _window
    0.07
     rolling
    0.07
    Activations Density 0.100%

    No Known Activations