© 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 EvalsExportsAPI 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. 56202
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to management and organizational processes

    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
     Hlav
    -0.07
    ãĥĸãĥª
    -0.06
    stem
    -0.06
    optgroup
    -0.06
    ingo
    -0.06
     Bark
    -0.06
    acker
    -0.06
    sti
    -0.06
    arLayout
    -0.06
    еÑĢжав
    -0.06
    POSITIVE LOGITS
     Records
    0.07
     lawful
    0.07
    Records
    0.07
    ÏĨοÏģ
    0.07
    records
    0.07
    ipse
    0.07
     records
    0.06
    ibold
    0.06
    Ī
    0.06
    TouchEvent
    0.06
    Activations Density 0.001%

    No Known Activations