© 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. 31372
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical treatments and their comparisons

    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
    mÃŃn
    -0.07
    ocache
    -0.07
    .slim
    -0.07
    iagnostics
    -0.07
    oltip
    -0.06
    esel
    -0.06
    SSIP
    -0.06
    ｡
    -0.06
    .DataContext
    -0.06
    istar
    -0.06
    POSITIVE LOGITS
     superior
    0.17
     superiority
    0.14
     Superior
    0.14
     performance
    0.12
    æ¯Ķ
    0.11
     compared
    0.11
     efficiency
    0.10
    æķĪ
    0.10
     Compared
    0.10
     performances
    0.09
    Activations Density 0.082%

    No Known Activations