© 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. 88768
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental sustainability and cleaning products

    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
    evin
    -0.07
    xon
    -0.07
    ض
    -0.07
    ÄįenÃŃ
    -0.07
    umberland
    -0.06
    oÄŁ
    -0.06
    abase
    -0.06
    бо
    -0.06
     Fo
    -0.06
    λαμβ
    -0.06
    POSITIVE LOGITS
    arget
    0.07
    iii
    0.06
    ried
    0.06
    ħ
    0.06
     high
    0.06
     ÑĢÑıдом
    0.06
     Hass
    0.06
    Ltd
    0.06
    nia
    0.06
     highs
    0.06
    Activations Density 0.038%

    No Known Activations