© 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. 94810
    Prev
    Next
    INDEX
    Explanations

    combinatorial patterns of capital letters that likely represent proper nouns or acronyms

    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
    cape
    -0.07
    æŁĦ
    -0.07
    hei
    -0.07
    MMdd
    -0.07
    hle
    -0.06
    zione
    -0.06
    :async
    -0.06
    curacy
    -0.06
    /Search
    -0.06
     UD
    -0.06
    POSITIVE LOGITS
    IEW
    0.07
    Äįet
    0.07
    éĻ£
    0.06
    inflate
    0.06
    .console
    0.06
    ignon
    0.06
     verdiÄŁi
    0.06
    icia
    0.06
    ellas
    0.06
    IEWS
    0.06
    Activations Density 0.018%

    No Known Activations