© 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. 17-LLAMASCOPE-RES-131K
    11. 15991
    Prev
    Next
    INDEX
    Explanations

    terms related to data centers and technical infrastructure

    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
    iros
    -0.07
    geries
    -0.07
    odon
    -0.07
    bih
    -0.07
    canf
    -0.07
     (*((
    -0.07
    ãĥ¼ãĥĦ
    -0.06
    poon
    -0.06
     Catal
    -0.06
     Mu
    -0.06
    POSITIVE LOGITS
     physical
    0.08
     facility
    0.08
     Cooling
    0.07
     storage
    0.07
     Storage
    0.07
     rack
    0.07
     cooling
    0.07
     Physical
    0.07
     coloc
    0.07
     Blades
    0.07
    Activations Density 0.006%

    No Known Activations