© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 96438
    Prev
    Next
    INDEX
    Explanations

    terms related to dental procedures and materials

    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
    ãĥ©ãĥĥãĤ¯
    -0.07
    ange
    -0.07
    abox
    -0.06
    Matchers
    -0.06
    orr
    -0.06
    ýv
    -0.06
     bufio
    -0.06
    ANGE
    -0.06
    edin
    -0.06
    rawer
    -0.06
    POSITIVE LOGITS
    ÄĻż
    0.07
     Warner
    0.06
    apr
    0.06
     WARN
    0.06
    297
    0.06
    otropic
    0.06
     Wid
    0.06
    reesome
    0.06
    nier
    0.06
     Lar
    0.06
    Activations Density 0.012%

    No Known Activations