© 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. 17-LLAMASCOPE-RES-131K
    11. 59689
    Prev
    Next
    INDEX
    Explanations

    the word "current" in various contexts

    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
    Ì
    -0.08
    annes
    -0.07
     srd
    -0.06
    iaux
    -0.06
    antu
    -0.06
     previously
    -0.06
    ern
    -0.06
    al
    -0.06
    hub
    -0.06
    ÙĪØ·
    -0.06
    POSITIVE LOGITS
    -day
    0.11
    /current
    0.10
    /form
    0.10
    ;y
    0.10
     affairs
    0.09
    mente
    0.09
    -generation
    0.09
    877
    0.09
    /latest
    0.09
    aneously
    0.09
    Activations Density 0.044%

    No Known Activations