© 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. 28112
    Prev
    Next
    INDEX
    Explanations

    key metrics and categories related to sports equipment pricing

    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
    kul
    -0.07
    è½®
    -0.06
    访
    -0.06
     autop
    -0.06
    輪
    -0.06
    ogi
    -0.06
    wire
    -0.06
    996
    -0.06
    dale
    -0.06
     ÑĤеÑĩ
    -0.06
    POSITIVE LOGITS
     manufact
    0.08
    .sourceforge
    0.08
     manufacture
    0.07
     manufacturing
    0.07
     Manufacturing
    0.07
    .getOutputStream
    0.07
     Rage
    0.07
     technolog
    0.07
     Centers
    0.07
     blade
    0.07
    Activations Density 0.002%

    No Known Activations