© 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. 41772
    Prev
    Next
    INDEX
    Explanations

    comparisons regarding price and quality of services or products

    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
    âĢ¦
    -0.07
    âĢ¦and
    -0.06
    oret
    -0.06
    âĢ¦the
    -0.06
    ac
    -0.06
    ↵
    -0.06
    ino
    -0.06
    .âĢ¦
    -0.06
    is
    -0.05
    âĢ¦↵
    -0.05
    POSITIVE LOGITS
    ếp
    0.08
    //{{
    0.08
    ÑĢод
    0.08
    MainFrame
    0.08
    лиÑĪком
    0.07
    odÃŃ
    0.07
    Clr
    0.07
    ÏįÏĦε
    0.07
    ÃĹ</
    0.07
    kaar
    0.07
    Activations Density 0.002%

    No Known Activations