© 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 EvalsExportsinterp-engineNEWAPI 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. 2652
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements related to waste disposal and dumpsters

    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
    èĨ
    -0.07
    é«
    -0.06
    úsqueda
    -0.06
    LAN
    -0.06
    elman
    -0.06
    .ss
    -0.06
     вд
    -0.06
    utin
    -0.05
     pump
    -0.05
    usz
    -0.05
    POSITIVE LOGITS
    SWG
    0.07
    \CMS
    0.07
     binh
    0.07
    webdriver
    0.07
     Allied
    0.07
    idor
    0.07
    ocht
    0.06
    ourd
    0.06
    _ASSUME
    0.06
    ublik
    0.06
    Activations Density 0.003%

    No Known Activations