© 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. 9-LLAMASCOPE-RES-131K
    11. 97003
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare and HIV/AIDS management

    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
    .scalablytyped
    -0.08
    tright
    -0.07
    оÑģÑĥд
    -0.07
    СÐŀ
    -0.07
    è¾°
    -0.07
    mlink
    -0.07
    /up
    -0.07
    blink
    -0.07
    ÑĮи
    -0.07
    eson
    -0.07
    POSITIVE LOGITS
     Bour
    0.06
    kits
    0.06
    Opts
    0.06
     DNA
    0.06
    _opts
    0.05
    0.05
    hole
    0.05
     pause
    0.05
     Archives
    0.05
    bac
    0.05
    Activations Density 0.013%

    No Known Activations