© 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. 38745
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terminology related to supplements and dietary ingredients

    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
    razier
    -0.07
     rodin
    -0.06
    Ø°
    -0.06
    ison
    -0.06
    во
    -0.06
    izon
    -0.06
    wdx
    -0.06
    eria
    -0.06
     environmental
    -0.06
    zes
    -0.06
    POSITIVE LOGITS
    åĿĽ
    0.07
    æŃ²
    0.07
    ADF
    0.07
    ubat
    0.07
    ế
    0.07
    -any
    0.07
     any
    0.06
    htable
    0.06
    à¸Ľà¸£
    0.06
    .ptr
    0.06
    Activations Density 0.016%

    No Known Activations