© 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. 27815
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions, requirements, or compliance

    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
    nes
    -0.07
    Įĵ
    -0.07
    adesh
    -0.07
    tems
    -0.06
    unar
    -0.06
    PropertyDescriptor
    -0.06
    niej
    -0.06
     McM
    -0.06
    оÑı
    -0.06
     par
    -0.06
    POSITIVE LOGITS
    è¿Ļ个
    0.10
     this
    0.10
    this
    0.09
     these
    0.08
    è¿Ļä¸Ģ
    0.08
    éĤ£ä¸ª
    0.07
    =this
    0.07
    	this
    0.07
     ÑįÑĤоÑĤ
    0.07
    these
    0.07
    Activations Density 0.029%

    No Known Activations