© 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. 107807
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical and geometrical theories

    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
    æłª
    -0.07
    abbo
    -0.07
    iris
    -0.06
    qrt
    -0.06
    ovice
    -0.06
    archy
    -0.06
     çľ
    -0.06
     رض
    -0.06
    ylon
    -0.06
    quier
    -0.06
    POSITIVE LOGITS
    ارÙģ
    0.06
    .rd
    0.06
    implify
    0.06
    ̣
    0.06
    vo
    0.06
     nek
    0.06
    ä¿Ŀ
    0.06
    иÑĤом
    0.06
    ÐĴÐŀ
    0.06
    alsy
    0.06
    Activations Density 0.050%

    No Known Activations