© 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. 117623
    Prev
    Next
    INDEX
    Explanations

    phrases related to bounded mathematical domains and equations

    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
    atan
    -0.07
    ibri
    -0.07
    uib
    -0.06
    ogh
    -0.06
    igkeit
    -0.06
    ecz
    -0.06
     inhabit
    -0.06
    adan
    -0.06
    uffer
    -0.06
    ειο
    -0.06
    POSITIVE LOGITS
     Olympic
    0.07
    USTER
    0.07
     vál
    0.06
    388
    0.06
     Perf
    0.06
     Caul
    0.06
     Forum
    0.06
     domest
    0.06
     batching
    0.06
     khuôn
    0.06
    Activations Density 0.213%

    No Known Activations