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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76281
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical concepts and structures, particularly involving Grassmann manifolds

    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
     prime
    -0.10
     primes
    -0.07
     Prime
    -0.07
    ugen
    -0.07
     peak
    -0.07
    Prime
    -0.07
    erca
    -0.06
     spi
    -0.06
    prime
    -0.06
    spi
    -0.06
    POSITIVE LOGITS
     space
    0.11
    space
    0.10
     vectors
    0.09
    .space
    0.09
     spaces
    0.09
     dimensions
    0.08
    Space
    0.08
     prostoru
    0.08
     hypers
    0.08
     espacio
    0.08
    Activations Density 0.215%

    No Known Activations