© 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. 598
    Prev
    Next
    INDEX
    Explanations

    terminology related to research methodology and governance in developing countries

    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
    åªĴ
    -0.07
    uben
    -0.07
     آذ
    -0.07
    glich
    -0.06
    _nat
    -0.06
     atol
    -0.06
    chai
    -0.06
    peria
    -0.06
    ubo
    -0.06
     defeat
    -0.06
    POSITIVE LOGITS
     fuzzy
    0.07
    orman
    0.07
    ecer
    0.07
    ipro
    0.06
    ãĤ¹ãĥŀ
    0.06
    ERA
    0.06
    лÑĥÑĪ
    0.06
     Hod
    0.06
    uzzy
    0.06
    isma
    0.06
    Activations Density 0.077%

    No Known Activations