© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89302
    Prev
    Next
    INDEX
    Explanations

    instances of the word "circulating" and its variations

    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
    child
    -0.07
    kol
    -0.07
    лод
    -0.06
    immel
    -0.06
    ertility
    -0.06
    à¸ĩà¸Ħ
    -0.06
     Wayback
    -0.06
    mouth
    -0.06
    اÙģÙĩ
    -0.06
    izard
    -0.06
    POSITIVE LOGITS
    -around
    0.10
    around
    0.09
    orp
    0.08
     among
    0.08
    among
    0.08
     amongst
    0.07
     throughout
    0.07
    é±
    0.07
    /upload
    0.07
    antes
    0.07
    Activations Density 0.007%

    No Known Activations