© 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 EvalsExportsinterp-engineNEWAPI 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. 54830
    Prev
    Next
    INDEX
    Explanations

    keywords related to decorative elements and aesthetics

    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
    vider
    -0.07
    mall
    -0.07
     bench
    -0.06
    æķ¦
    -0.06
     leather
    -0.06
    egis
    -0.06
    ewed
    -0.06
    yles
    -0.06
    _Lean
    -0.06
    cloth
    -0.06
    POSITIVE LOGITS
    /GL
    0.07
    particles
    0.07
    obus
    0.07
    stars
    0.07
     stars
    0.07
     particles
    0.06
     оÑĤдел
    0.06
    /gl
    0.06
     bach
    0.06
    _particles
    0.06
    Activations Density 0.011%

    No Known Activations