© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87874
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses

    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
     ancest
    -0.07
    REW
    -0.07
    inch
    -0.07
    resolution
    -0.07
    trak
    -0.06
    наÑĢ
    -0.06
    esk
    -0.06
    ariant
    -0.06
    aq
    -0.06
    inati
    -0.06
    POSITIVE LOGITS
    ebin
    0.08
    ansson
    0.07
    &o
    0.07
     Peaks
    0.07
    eyJ
    0.07
     IOCTL
    0.07
    eger
    0.07
    ÑĢавилÑĮ
    0.06
    rede
    0.06
     ConfigureServices
    0.06
    Activations Density 0.009%

    No Known Activations