© 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. 16740
    Prev
    Next
    INDEX
    Explanations

    medical terms related to infections and the urinary system

    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
    iosa
    -0.07
    íĩ´
    -0.07
    سب
    -0.06
    ois
    -0.06
    دد
    -0.06
    illez
    -0.06
    isp
    -0.06
     Dent
    -0.06
    Dll
    -0.06
    arih
    -0.06
    POSITIVE LOGITS
     Barrett
    0.08
    raquo
    0.06
    agus
    0.06
    lete
    0.06
    gy
    0.06
    xbb
    0.06
    .gf
    0.06
    awk
    0.06
    anness
    0.06
    otland
    0.06
    Activations Density 0.003%

    No Known Activations