© 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. 72411
    Prev
    Next
    INDEX
    Explanations

    phrases related to partial derivatives and mathematical modeling

    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
    ãĥ©ãĥĥãĤ¯
    -0.08
    ese
    -0.08
    æł·çļĦ
    -0.07
    making
    -0.07
    elier
    -0.07
    سد
    -0.07
    ulp
    -0.07
    enberg
    -0.07
    seed
    -0.07
    SCRI
    -0.06
    POSITIVE LOGITS
    /full
    0.12
    ities
    0.10
    ity
    0.10
    mente
    0.09
    idades
    0.08
    ty
    0.08
    ties
    0.08
    cular
    0.07
    ités
    0.07
    ize
    0.07
    Activations Density 0.013%

    No Known Activations