© 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. 15-LLAMASCOPE-RES-131K
    6. 66
    Prev
    Next
    INDEX
    Explanations

    discussions about disciplinary overlaps and gaps in scholarly research

    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
     backed
    -0.07
     plan
    -0.07
    úa
    -0.06
     Kul
    -0.06
     anthrop
    -0.06
    xima
    -0.06
    HWND
    -0.06
    vl
    -0.06
    kee
    -0.06
    uw
    -0.06
    POSITIVE LOGITS
     Caucus
    0.08
     caut
    0.08
    utor
    0.07
    .cg
    0.07
    ä¸ĢåĮº
    0.07
     bund
    0.07
    .AutoComplete
    0.07
    .LookAndFeel
    0.06
     Selbst
    0.06
    ductive
    0.06
    Activations Density 0.005%

    No Known Activations