© 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. 72837
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to market statistics and supply chains

    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
    astically
    -0.06
    amo
    -0.06
    fault
    -0.06
    ầm
    -0.06
     reserve
    -0.06
    zman
    -0.05
    igma
    -0.05
    ented
    -0.05
    dio
    -0.05
    retry
    -0.05
    POSITIVE LOGITS
    chwitz
    0.08
    asal
    0.08
    osate
    0.08
    ãĥ¼ãĥª
    0.07
     revenue
    0.07
    ÙĦع
    0.07
    वर
    0.07
    IFIC
    0.07
    OLUTE
    0.06
    /loose
    0.06
    Activations Density 0.000%

    No Known Activations