© 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. 80089
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to boundary conditions in mathematical simulations

    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
    å¾½
    -0.07
    bet
    -0.07
    ELLOW
    -0.06
    ANA
    -0.06
    ivi
    -0.06
    hip
    -0.06
     Elias
    -0.06
    azon
    -0.06
     Ange
    -0.06
    _FORE
    -0.06
    POSITIVE LOGITS
     boundary
    0.20
     Boundary
    0.18
    boundary
    0.17
    Boundary
    0.15
     boundaries
    0.14
     border
    0.13
    _boundary
    0.13
    oundary
    0.12
     Border
    0.11
    è¾¹
    0.11
    Activations Density 0.281%

    No Known Activations