© 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. 81191
    Prev
    Next
    INDEX
    Explanations

    references to environmental conservation and preservation efforts

    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
    ething
    -0.06
    ushima
    -0.06
    oupon
    -0.06
    idine
    -0.06
    PathVariable
    -0.06
    issuer
    -0.06
     Fior
    -0.06
     ÐĴики
    -0.06
    à¥įà¤
    -0.06
     диÑģ
    -0.06
    POSITIVE LOGITS
     land
    0.08
     Conservation
    0.07
     eas
    0.07
     buffers
    0.07
     buffer
    0.07
     property
    0.07
     protection
    0.07
     conservation
    0.07
     Buffer
    0.07
    inois
    0.07
    Activations Density 0.002%

    No Known Activations