© 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. 17-LLAMASCOPE-RES-131K
    11. 15894
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures and collections in programming

    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
    Å¡Å¥
    -0.07
    /******/
    -0.07
    ksen
    -0.07
    /stdc
    -0.06
    .MixedReality
    -0.06
    WhiteSpace
    -0.06
    .ide
    -0.06
    家æĹı
    -0.06
    addons
    -0.06
    pressive
    -0.06
    POSITIVE LOGITS
     int
    0.07
    ucci
    0.06
     of
    0.06
     deferred
    0.06
     Closure
    0.06
     volumes
    0.06
    ula
    0.06
     Jew
    0.06
    IA
    0.06
     Blast
    0.06
    Activations Density 0.009%

    No Known Activations