© 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. 79985
    Prev
    Next
    INDEX
    Explanations

    important and significant terms related to recognition and eligibility

    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
    ioni
    -0.07
    ãİ
    -0.07
     disg
    -0.07
     ÄĮer
    -0.07
    ¦æĥħ
    -0.07
    lük
    -0.07
    ìľ¼ëĭĪ
    -0.07
    çĻ»
    -0.06
    _MASK
    -0.06
    inya
    -0.06
    POSITIVE LOGITS
    ourcem
    0.07
    oker
    0.06
    coder
    0.06
    ï¼ł
    0.06
    imat
    0.06
    ILLE
    0.06
    outil
    0.06
    lon
    0.05
    /Typography
    0.05
    ospace
    0.05
    Activations Density 0.000%

    No Known Activations