© 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. 78327
    Prev
    Next
    INDEX
    Explanations

    key moments or events that signify significant changes in history or concepts

    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
    331
    -0.08
    ime
    -0.07
    SGlobal
    -0.07
    оÑĩнÑĭÑħ
    -0.07
    lander
    -0.07
    ele
    -0.07
    .Classes
    -0.06
     sür
    -0.06
    @student
    -0.06
    .LookAndFeel
    -0.06
    POSITIVE LOGITS
     finally
    0.11
     begin
    0.10
     begins
    0.10
    -switch
    0.10
     switch
    0.09
    finally
    0.09
     officially
    0.09
     artık
    0.09
    switch
    0.09
    æŃ£å¼ı
    0.08
    Activations Density 0.064%

    No Known Activations