© 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. 90787
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or usefulness

    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
    Ñĥли
    -0.07
     gross
    -0.07
    eller
    -0.07
     others
    -0.06
    uez
    -0.06
    hee
    -0.06
    gross
    -0.06
    ÑĢан
    -0.06
     elsewhere
    -0.06
    ifest
    -0.06
    POSITIVE LOGITS
    ssa
    0.08
    GetCurrent
    0.07
    raf
    0.07
    Moder
    0.07
    égor
    0.07
    luk
    0.07
    ãĥ©ãĥĥãĤ¯
    0.07
    åİŁæĿ¥
    0.07
    ÑĪка
    0.07
    andi
    0.06
    Activations Density 0.018%

    No Known Activations