© 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. 5575
    Prev
    Next
    INDEX
    Explanations

    technical processes related to energy conversion and signal generation

    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
    zar
    -0.06
    ÑĢÑĥÑģ
    -0.06
     recent
    -0.06
    öst
    -0.06
    ipy
    -0.06
    EMBER
    -0.06
    seau
    -0.06
    amer
    -0.06
    quo
    -0.05
    баÑĩ
    -0.05
    POSITIVE LOGITS
    avia
    0.08
     nên
    0.07
    æł·åŃIJ
    0.06
    basis
    0.06
    PELL
    0.06
    anel
    0.06
     lah
    0.06
     Dün
    0.06
     eventual
    0.06
     вполне
    0.06
    Activations Density 0.034%

    No Known Activations