© 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. 78461
    Prev
    Next
    INDEX
    Explanations

    information related to seating and capacity statistics in various contexts

    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
    $MESS
    -0.07
    ogy
    -0.07
    ãĥ¼ãĥį
    -0.07
    .histogram
    -0.07
    rgan
    -0.07
    swick
    -0.07
    ibraries
    -0.07
    mtree
    -0.06
     addCriterion
    -0.06
    activex
    -0.06
    POSITIVE LOGITS
     capacity
    0.17
    capacity
    0.14
     Capacity
    0.14
    Capacity
    0.13
     capacities
    0.11
     capacidad
    0.11
    _capacity
    0.10
    .capacity
    0.10
     capability
    0.10
     maximum
    0.09
    Activations Density 0.016%

    No Known Activations