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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26676
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships and properties regarding sets and their elements

    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
    VEL
    -0.06
    ResourceId
    -0.06
     Grant
    -0.06
    raf
    -0.06
    онÑĮ
    -0.06
    ysl
    -0.06
    enburg
    -0.06
    Grant
    -0.06
    undo
    -0.06
     Su
    -0.06
    POSITIVE LOGITS
    arry
    0.07
     Morales
    0.06
     wÅĤa
    0.06
    walls
    0.06
    ary
    0.06
    ervo
    0.06
    rong
    0.06
    inese
    0.06
     Bearing
    0.06
    aily
    0.06
    Activations Density 0.071%

    No Known Activations