© 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. 17-LLAMASCOPE-RES-131K
    11. 2621
    Prev
    Next
    INDEX
    Explanations

    terms related to kidney function and urine excretion

    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
    овиÑĩ
    -0.06
     gost
    -0.06
     влад
    -0.06
    αιδ
    -0.06
    arian
    -0.06
     togg
    -0.06
     gratuit
    -0.06
     plast
    -0.06
    ei
    -0.06
     Fet
    -0.06
    POSITIVE LOGITS
     expelled
    0.07
     expulsion
    0.07
    orp
    0.07
     exits
    0.07
    abee
    0.07
    åĩºåİ»
    0.07
    .flush
    0.07
     exit
    0.07
     вÑĭвод
    0.07
    isque
    0.07
    Activations Density 0.012%

    No Known Activations