© 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. 72122
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related terminology

    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
    ib
    -0.07
    orer
    -0.07
     logistics
    -0.06
    unj
    -0.06
     narr
    -0.06
    ay
    -0.06
    oot
    -0.06
     Paige
    -0.06
     fore
    -0.06
     Dy
    -0.06
    POSITIVE LOGITS
     EXAMPLE
    0.09
    notes
    0.08
    _example
    0.08
     example
    0.08
    example
    0.08
    Example
    0.08
     Example
    0.08
     NOTES
    0.08
     ÙħثاÙĦ
    0.08
    _note
    0.07
    Activations Density 0.031%

    No Known Activations