© 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 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. 17-LLAMASCOPE-RES-131K
    11. 126591
    Prev
    Next
    INDEX
    Explanations

    discussions related to public health systems and financial organizations

    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
    owo
    -0.07
    chied
    -0.06
    ÑĢÑĥз
    -0.06
    oom
    -0.06
    ucci
    -0.06
    cop
    -0.06
    loys
    -0.06
    è¿ij
    -0.05
    /misc
    -0.05
     faithfully
    -0.05
    POSITIVE LOGITS
     would
    0.10
    would
    0.09
     Would
    0.09
    Would
    0.09
    ãĤĴä½ľ
    0.07
     eventual
    0.07
     zou
    0.07
    _based
    0.07
     proposal
    0.07
    ateria
    0.07
    Activations Density 0.081%

    No Known Activations