© 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. 124298
    Prev
    Next
    INDEX
    Explanations

    terms related to water management and irrigation

    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
    ktop
    -0.07
    charm
    -0.06
    ptic
    -0.06
     sokak
    -0.06
    orque
    -0.06
     законом
    -0.06
     diver
    -0.06
    mmc
    -0.06
    quo
    -0.06
    rede
    -0.06
    POSITIVE LOGITS
    /resource
    0.07
     resource
    0.07
     weight
    0.07
    Earth
    0.06
     Earth
    0.06
    صÙĩ
    0.06
    ForResource
    0.06
    ipes
    0.06
     Ñģеб
    0.06
    御
    0.06
    Activations Density 0.002%

    No Known Activations