© 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. 72986
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of" in various contexts

    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
    еÑģÑı
    -0.08
    fik
    -0.07
    .activation
    -0.07
    æľŁ
    -0.07
    aeda
    -0.07
    uyá»ĥn
    -0.07
    ·æĸ°
    -0.07
    arım
    -0.07
    quette
    -0.07
    icrosoft
    -0.07
    POSITIVE LOGITS
     tests
    0.09
     efforts
    0.08
     ongoing
    0.08
     actions
    0.07
    Tests
    0.07
     investigations
    0.07
     experiments
    0.07
    ultan
    0.07
    tests
    0.06
     applying
    0.06
    Activations Density 0.032%

    No Known Activations