© 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. 56205
    Prev
    Next
    INDEX
    Explanations

    terms related to business operations and management

    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
    inton
    -0.07
    IRC
    -0.07
    achi
    -0.06
    ÑĢак
    -0.06
     lep
    -0.06
    kul
    -0.06
    (er
    -0.06
    prak
    -0.06
    коз
    -0.06
    dere
    -0.06
    POSITIVE LOGITS
    ize
    0.10
    elize
    0.08
    763
    0.07
    oufl
    0.07
    _traits
    0.07
     lại
    0.07
     sobie
    0.07
    ujet
    0.07
    ify
    0.07
    ted
    0.07
    Activations Density 0.096%

    No Known Activations