© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94800
    Prev
    Next
    INDEX
    Explanations

    concepts related to dynamic programming and optimization algorithms

    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
    sanitize
    -0.07
    otti
    -0.07
    OnInit
    -0.07
    ï¼ĪæĺŃåĴĮ
    -0.07
    vro
    -0.07
    _initializer
    -0.07
    ä¸Ī
    -0.07
    ÙĪÙĤت
    -0.07
    ожеÑĤ
    -0.07
     ÐĿÑĸ
    -0.07
    POSITIVE LOGITS
    tor
    0.06
     Ear
    0.06
    .Framework
    0.06
    ester
    0.06
    143
    0.06
    abit
    0.05
    ÙĬدا
    0.05
    .gc
    0.05
    aser
    0.05
    rent
    0.05
    Activations Density 0.056%

    No Known Activations