© 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. 9-LLAMASCOPE-RES-131K
    11. 98621
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to determinants in linear algebra

    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
     met
    -0.07
    igli
    -0.06
    ÅĻed
    -0.06
    cka
    -0.06
    /projects
    -0.06
    tec
    -0.06
    orman
    -0.06
    åĪ°çļĦ
    -0.06
     prolifer
    -0.06
     vag
    -0.06
    POSITIVE LOGITS
    adius
    0.07
     POSSIBILITY
    0.06
    dyn
    0.06
    reator
    0.06
    ersed
    0.06
    sts
    0.06
    _above
    0.06
    orca
    0.06
    plib
    0.06
    istream
    0.06
    Activations Density 0.016%

    No Known Activations