© 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. 79483
    Prev
    Next
    INDEX
    Explanations

    references to natural resources and outdoor activities

    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
    ityEngine
    -0.07
     cazzo
    -0.07
    NullException
    -0.07
    ecko
    -0.07
    _dw
    -0.06
    hev
    -0.06
    ãĥ¼ãĥ«
    -0.06
    gan
    -0.06
    /GPL
    -0.06
    lom
    -0.06
    POSITIVE LOGITS
     Private
    0.07
    management
    0.06
    _Integer
    0.06
    eder
    0.06
     prime
    0.06
    arlar
    0.06
     MIX
    0.06
    kı
    0.06
     rin
    0.06
    æĶ¾
    0.06
    Activations Density 0.001%

    No Known Activations