© 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. 88011
    Prev
    Next
    INDEX
    Explanations

    terms related to copyright and permissions

    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
    anner
    -0.08
    икÑĥ
    -0.07
    ums
    -0.07
    лада
    -0.07
    kiye
    -0.06
    ingle
    -0.06
    Ñĸка
    -0.06
    _plural
    -0.06
    gow
    -0.06
    construct
    -0.06
    POSITIVE LOGITS
    holm
    0.07
    ẫ
    0.06
     Morrow
    0.06
     physic
    0.06
    wine
    0.06
    efon
    0.06
    vla
    0.06
    chap
    0.06
    ucc
    0.05
     sinus
    0.05
    Activations Density 0.001%

    No Known Activations