© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27555
    Prev
    Next
    INDEX
    Explanations

    terms related to the urinary system and its functions

    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
     competition
    -0.06
    linky
    -0.06
    verty
    -0.06
     underlying
    -0.06
    chai
    -0.06
     insurg
    -0.06
    anos
    -0.06
    zk
    -0.06
    BO
    -0.05
    rap
    -0.05
    POSITIVE LOGITS
    ÑĢаж
    0.08
    κÏħ
    0.07
    isEnabled
    0.07
    окон
    0.07
     bol
    0.07
     fur
    0.07
    ocio
    0.07
    ocytes
    0.07
    ÑĢиÑĩ
    0.07
    riangle
    0.07
    Activations Density 0.011%

    No Known Activations