© 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. 15-LLAMASCOPE-RES-131K
    11. 88093
    Prev
    Next
    INDEX
    Explanations

    technical terms related to pump sealing systems

    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
     oppon
    -0.07
    referrer
    -0.06
    etable
    -0.06
    viso
    -0.06
    æĸ
    -0.06
    recipe
    -0.06
    à¹Īà¸Ńà¸Ļ
    -0.06
    à¹Ĥà¸ģ
    -0.06
    _roll
    -0.06
    bÃŃr
    -0.06
    POSITIVE LOGITS
     water
    0.07
     pumps
    0.07
     pump
    0.07
    anst
    0.07
     Water
    0.06
    alf
    0.06
     ãĤ¢ãĤ¤
    0.06
     pumping
    0.06
     fluid
    0.06
     Rated
    0.06
    Activations Density 0.005%

    No Known Activations