© 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. 42115
    Prev
    Next
    INDEX
    Explanations

    references to mosquito prevention and breeding grounds in outdoor 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
     version
    -0.07
    -f
    -0.07
    nock
    -0.06
    allet
    -0.06
    iew
    -0.06
    ä¸Ģç§į
    -0.05
     matching
    -0.05
     versions
    -0.05
    fp
    -0.05
     fie
    -0.05
    POSITIVE LOGITS
    lesi
    0.08
     PARTICULAR
    0.07
     serg
    0.07
    782
    0.07
    andalone
    0.07
    ãn
    0.07
     jadx
    0.07
    HAV
    0.07
    AME
    0.07
    ÃŃÅ¡
    0.07
    Activations Density 0.018%

    No Known Activations