© 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. 14686
    Prev
    Next
    INDEX
    Explanations

    prefixes or suffixes that indicate variations of the term "non-rigid" in the context of scientific terminology

    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
    ARGIN
    -0.08
    stad
    -0.07
     zwar
    -0.07
    stadt
    -0.07
    jen
    -0.07
    borough
    -0.07
    ritch
    -0.07
    agra
    -0.06
    sass
    -0.06
    shaw
    -0.06
    POSITIVE LOGITS
    /non
    0.11
    etheless
    0.07
    /not
    0.07
    edly
    0.07
     åij
    0.06
    ilibrium
    0.06
    (non
    0.06
     Careers
    0.06
    Stop
    0.06
    reau
    0.06
    Activations Density 0.023%

    No Known Activations