© 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. 72043
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as keywords and visibility modifiers in programming

    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
     Pron
    -0.08
    _mpi
    -0.06
    argest
    -0.06
     dol
    -0.06
    .sav
    -0.06
    undaki
    -0.06
    awan
    -0.06
    ibaba
    -0.06
     rev
    -0.06
     Econ
    -0.06
    POSITIVE LOGITS
     lateinit
    0.08
     locally
    0.06
    erais
    0.06
    _defs
    0.06
     Universe
    0.06
    reet
    0.06
     roadside
    0.06
    emain
    0.06
     universally
    0.06
     Hou
    0.06
    Activations Density 0.002%

    No Known Activations