© 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. 2564
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation for rare qualities or experiences in professional or personal interactions

    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
    lü
    -0.07
    inas
    -0.07
    emer
    -0.07
    estar
    -0.07
    enas
    -0.07
    ACCESS
    -0.06
    aget
    -0.06
    ülük
    -0.06
    isd
    -0.06
    é
    -0.06
    POSITIVE LOGITS
     elsewhere
    0.08
     other
    0.07
     rare
    0.07
    rome
    0.06
    asin
    0.06
     anymore
    0.06
     rarity
    0.06
     alas
    0.06
    359
    0.06
    inkle
    0.06
    Activations Density 0.015%

    No Known Activations