© 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. 80297
    Prev
    Next
    INDEX
    Explanations

    terms related to wetlands and their ecological characteristics

    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
    naires
    -0.08
     gá»ijc
    -0.08
    eer
    -0.07
    frei
    -0.07
    ogany
    -0.07
    égor
    -0.07
    AGED
    -0.07
    nze
    -0.07
    tiv
    -0.07
    ippi
    -0.07
    POSITIVE LOGITS
    zel
    0.08
    ted
    0.07
    eland
    0.06
     fore
    0.06
    lands
    0.06
     rec
    0.06
    tring
    0.06
    wang
    0.06
    coat
    0.06
    gem
    0.06
    Activations Density 0.003%

    No Known Activations