© 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. 108325
    Prev
    Next
    INDEX
    Explanations

    phrases related to metrics and evaluation of data

    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
    lý
    -0.07
    ViewInit
    -0.06
    asco
    -0.06
    classify
    -0.06
    DECL
    -0.06
    lisi
    -0.06
    GNUC
    -0.06
    nik
    -0.06
     magna
    -0.06
    /views
    -0.06
    POSITIVE LOGITS
     uom
    0.07
     Cot
    0.07
     measurement
    0.07
    ingle
    0.06
    etting
    0.06
    urch
    0.06
    .createTextNode
    0.06
     Monitoring
    0.06
     Universe
    0.06
    Monitoring
    0.06
    Activations Density 0.003%

    No Known Activations