© 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. 106622
    Prev
    Next
    INDEX
    Explanations

    references to osmosis and its effects on organisms and their environments

    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
    ivos
    -0.07
    eyin
    -0.06
     onRequest
    -0.06
     keyst
    -0.06
    Deg
    -0.06
     pir
    -0.06
    EIF
    -0.06
    æ°§
    -0.06
    eyen
    -0.06
    antry
    -0.06
    POSITIVE LOGITS
     water
    0.08
     os
    0.07
    water
    0.07
     Vern
    0.07
    isco
    0.07
    _water
    0.06
    inside
    0.06
     Boyle
    0.06
     inside
    0.06
     Inside
    0.06
    Activations Density 0.013%

    No Known Activations