© 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 EvalsExportsAPI 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. 87393
    Prev
    Next
    INDEX
    Explanations

    features related to health tracking and progress monitoring in wellness programs

    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
    -0.06
     saturation
    -0.05
     Russell
    -0.05
     res
    -0.05
    uem
    -0.05
    ierz
    -0.05
     radio
    -0.05
     backgrounds
    -0.05
    ion
    -0.05
    de
    -0.05
    POSITIVE LOGITS
    trecht
    0.08
    é¼ĵ
    0.08
    _keeper
    0.07
    лам
    0.07
    (exports
    0.07
     EXPORT
    0.07
    ÑĢава
    0.07
     graphs
    0.07
    -svg
    0.07
    Ñĩив
    0.07
    Activations Density 0.014%

    No Known Activations