© 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. 15-LLAMASCOPE-RES-131K
    11. 87994
    Prev
    Next
    INDEX
    Explanations

    terms related to substance use and addiction

    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
    olet
    -0.07
    dio
    -0.07
    ãĥªãĥ¼ãĤº
    -0.06
    à¸Ķà¸ĩ
    -0.06
    upp
    -0.06
    KeyType
    -0.06
    tring
    -0.06
    tras
    -0.06
    omatic
    -0.06
    universal
    -0.06
    POSITIVE LOGITS
     synthetic
    0.08
     substances
    0.07
     misuse
    0.07
     Eastern
    0.07
     drugs
    0.07
     إد
    0.07
     McK
    0.06
    شب
    0.06
     RectTransform
    0.06
    -use
    0.06
    Activations Density 0.016%

    No Known Activations