© 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. 81649
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations related to vector spaces and linear algebra concepts

    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
    rais
    -0.07
    IFO
    -0.07
    _Stream
    -0.06
    _exports
    -0.06
    prefs
    -0.06
    βο
    -0.06
     curses
    -0.06
     curse
    -0.06
    ompiler
    -0.06
    arma
    -0.06
    POSITIVE LOGITS
    bsite
    0.07
    оÑı
    0.06
     FileAccess
    0.06
    _MO
    0.06
    anza
    0.06
    stown
    0.06
     abandoned
    0.06
    ãĥ³ãĥij
    0.06
     Haw
    0.06
    avoid
    0.05
    Activations Density 0.056%

    No Known Activations