© 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. 17422
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'even' 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
    MLS
    -0.08
    ÙĪÙĨÙĩ
    -0.07
    achen
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
    itori
    -0.07
    ICH
    -0.07
    ulin
    -0.06
    é¼»
    -0.06
    EventArgs
    -0.06
    ANCH
    -0.06
    POSITIVE LOGITS
    woff
    0.06
     challenging
    0.06
     ones
    0.06
     busiest
    0.06
     upwards
    0.06
     tight
    0.06
     complex
    0.06
    ué
    0.06
     demanding
    0.06
     extreme
    0.05
    Activations Density 0.015%

    No Known Activations