© 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. 71901
    Prev
    Next
    INDEX
    Explanations

    numerical representations of measurements or quantities

    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
    -mount
    -0.05
    worth
    -0.05
    opt
    -0.05
    İ
    -0.05
    enes
    -0.05
    _MALLOC
    -0.05
     lod
    -0.05
    lod
    -0.05
    ất
    -0.05
     spherical
    -0.05
    POSITIVE LOGITS
    ellar
    0.08
    TouchListener
    0.08
    subscriber
    0.07
    utas
    0.07
    hiro
    0.07
    agnet
    0.07
    _TestCase
    0.07
    anlı
    0.07
    suming
    0.07
    udo
    0.07
    Activations Density 0.116%

    No Known Activations