© 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. 105451
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables related to graph theory

    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
    æĺĩ
    -0.07
    ARB
    -0.07
    kenin
    -0.07
     uÄŁ
    -0.07
    seau
    -0.06
    اساÙĨ
    -0.06
     Ðŀп
    -0.06
    _SI
    -0.06
    ayın
    -0.06
     dzi
    -0.06
    POSITIVE LOGITS
     count
    0.08
     buy
    0.07
    ucher
    0.07
     fewer
    0.07
    count
    0.06
     number
    0.06
     bon
    0.06
     Stark
    0.06
     extra
    0.06
    ingle
    0.06
    Activations Density 0.109%

    No Known Activations