© 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. 17-LLAMASCOPE-RES-131K
    11. 57351
    Prev
    Next
    INDEX
    Explanations

    references to visual elements, specifically dots and points in descriptions

    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
    /tutorial
    -0.07
    oire
    -0.06
    orie
    -0.06
    elight
    -0.06
    .onStart
    -0.06
    UnderTest
    -0.06
    ymes
    -0.06
    ein
    -0.06
    t
    -0.06
    tainment
    -0.06
    POSITIVE LOGITS
    -dot
    0.10
    ting
    0.08
     зÑĢениÑı
    0.07
    åĦ¿
    0.07
     dot
    0.07
    regor
    0.07
    dot
    0.07
    712
    0.07
    fusc
    0.07
    ipelines
    0.07
    Activations Density 0.012%

    No Known Activations