© 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 EvalsExportsAPI 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. 130434
    Prev
    Next
    INDEX
    Explanations

    words associated with culinary herbs and their uses

    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
    æ¢Ŀ
    -0.07
    ÙĨاء
    -0.07
    æĿ¡
    -0.07
    _DH
    -0.07
    ãĥ«ãĤ¯
    -0.07
    Ñĭл
    -0.07
     neust
    -0.07
    _soft
    -0.06
    ÙĪزÛĮ
    -0.06
    selectedIndex
    -0.06
    POSITIVE LOGITS
     salt
    0.10
     taste
    0.10
     Salt
    0.09
     seasoning
    0.09
    Salt
    0.09
     season
    0.09
     Season
    0.08
     cond
    0.08
     Taste
    0.08
    salt
    0.08
    Activations Density 0.108%

    No Known Activations