© 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. 120929
    Prev
    Next
    INDEX
    Explanations

    references to the opening of new facilities or initiatives

    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
    HOOK
    -0.08
    oval
    -0.07
    поÑĢ
    -0.07
    loi
    -0.07
    908
    -0.07
    rod
    -0.07
    ãģĸ
    -0.07
    PagerAdapter
    -0.06
    ija
    -0.06
    rolls
    -0.06
    POSITIVE LOGITS
     branch
    0.09
     opened
    0.09
     doors
    0.08
    elper
    0.08
     new
    0.08
    /open
    0.08
     offices
    0.08
     branches
    0.08
    branch
    0.07
    æĸ°çļĦ
    0.07
    Activations Density 0.010%

    No Known Activations