© 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. 92751
    Prev
    Next
    INDEX
    Explanations

    indicators of statistical trends and changes over time

    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
     exponentially
    -0.07
    ÙĤب
    -0.07
    mdi
    -0.07
    ТÐŀ
    -0.07
    vailable
    -0.07
    æ·
    -0.07
    аÑĤÑĭ
    -0.07
    riott
    -0.06
    kommen
    -0.06
     archetype
    -0.06
    POSITIVE LOGITS
     Sud
    0.07
     trends
    0.06
    errat
    0.06
     Trends
    0.06
    kan
    0.06
     bo
    0.06
    isan
    0.06
     Mush
    0.06
    aur
    0.06
     Bryan
    0.05
    Activations Density 0.032%

    No Known Activations