© 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. 9-LLAMASCOPE-RES-131K
    11. 98405
    Prev
    Next
    INDEX
    Explanations

    terms related to digestion and digestive health

    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
    iper
    -0.07
    usage
    -0.06
    ipp
    -0.06
    aler
    -0.06
     mun
    -0.06
    ement
    -0.06
     dash
    -0.06
     coverage
    -0.06
    ecer
    -0.06
    itude
    -0.06
    POSITIVE LOGITS
    AtA
    0.07
     TMPro
    0.07
    .Contracts
    0.07
    ¤¤
    0.07
    -FIRST
    0.07
    _redirected
    0.07
     Trainer
    0.06
     tract
    0.06
    yat
    0.06
    linky
    0.06
    Activations Density 0.002%

    No Known Activations