© 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. 120287
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements and dimensions

    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
    оÑĢо
    -0.07
     layer
    -0.06
    dling
    -0.06
    mada
    -0.06
    isas
    -0.06
    æ²¢
    -0.06
    ear
    -0.06
     Mechan
    -0.06
    /false
    -0.06
    isa
    -0.06
    POSITIVE LOGITS
    _inches
    0.08
     measurements
    0.08
    寸
    0.08
     Kushner
    0.08
    =size
    0.07
    -height
    0.07
    :size
    0.07
     dimensions
    0.07
    ally
    0.07
     sizes
    0.07
    Activations Density 0.010%

    No Known Activations