© 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. 89029
    Prev
    Next
    INDEX
    Explanations

    phrases related to real-time processing and monitoring

    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
    евиÑĩ
    -0.08
    PageIndex
    -0.08
    ÐŁÐŀ
    -0.08
    ÑģÑıг
    -0.08
    IFO
    -0.08
     málo
    -0.07
    λια
    -0.07
    oya
    -0.07
    éĺħ读次æķ°
    -0.07
    .AddTransient
    -0.07
    POSITIVE LOGITS
    aneously
    0.10
    aneous
    0.09
    /live
    0.08
    /on
    0.07
    oxetine
    0.06
    rend
    0.06
    /in
    0.06
     live
    0.06
    othy
    0.05
     Hugo
    0.05
    Activations Density 0.005%

    No Known Activations