© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 59847
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology related to equations and calculations

    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
    _transient
    -0.07
    gle
    -0.06
    .setViewport
    -0.06
    FORMAT
    -0.06
    олог
    -0.06
    å¹ķ
    -0.06
    bee
    -0.06
     pil
    -0.06
    Æ°á»Ľ
    -0.06
     Colon
    -0.06
    POSITIVE LOGITS
     eigen
    0.07
     Eigen
    0.07
    ayar
    0.06
    addon
    0.06
     Hamilton
    0.06
    Hamilton
    0.06
     reco
    0.06
    unya
    0.06
    Eigen
    0.06
     Mexican
    0.06
    Activations Density 0.214%

    No Known Activations