© 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. 124730
    Prev
    Next
    INDEX
    Explanations

    phrases related to creative collaboration and community support 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
     almost
    -0.06
     usually
    -0.06
     was
    -0.06
     merely
    -0.06
     Kush
    -0.06
     sometimes
    -0.06
    _ram
    -0.06
    erspective
    -0.05
     entr
    -0.05
     nackte
    -0.05
    POSITIVE LOGITS
     vielleicht
    0.08
     additional
    0.08
    æĽ´å¤ļ
    0.08
    ecome
    0.08
     hopefully
    0.08
    ãĤĤãģ£ãģ¨
    0.08
    aremos
    0.08
     ourselves
    0.07
     next
    0.07
    æĽ´åĬł
    0.07
    Activations Density 0.042%

    No Known Activations