© 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. 15-LLAMASCOPE-RES-131K
    11. 87758
    Prev
    Next
    INDEX
    Explanations

    specific measurements, quantities, or values pertaining to recipes or ingredients

    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
    uve
    -0.08
    pected
    -0.06
    ARGIN
    -0.06
    ipel
    -0.06
    rzy
    -0.06
    loe
    -0.06
     Peters
    -0.06
    æĴ°
    -0.06
    artner
    -0.06
    InputElement
    -0.06
    POSITIVE LOGITS
     inform
    0.06
     Bundle
    0.06
     Bubble
    0.06
     Buddy
    0.06
     ter
    0.06
    ectors
    0.06
     pac
    0.06
    itaire
    0.06
     Pit
    0.06
    ridge
    0.06
    Activations Density 0.008%

    No Known Activations