© 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 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. 61101
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical concepts related to color and geometry

    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
    .utilities
    -0.07
     tuto
    -0.07
    ãģŁãģı
    -0.07
     dolar
    -0.07
    plib
    -0.07
    stup
    -0.07
    ÑĮв
    -0.07
    edis
    -0.06
     Ú©ÛĮÙģ
    -0.06
    pedido
    -0.06
    POSITIVE LOGITS
    ahl
    0.08
    owitz
    0.06
     Finally
    0.06
     finally
    0.06
    uy
    0.06
    åĩ
    0.06
    _DEPRECATED
    0.06
    imedia
    0.06
    finally
    0.05
    ↵
    0.05
    Activations Density 0.013%

    No Known Activations