© 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. 55331
    Prev
    Next
    INDEX
    Explanations

    words that indicate effort or difficulty

    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
     now
    -0.07
     recent
    -0.07
    ITTE
    -0.07
     currently
    -0.06
     Recent
    -0.06
     tonight
    -0.06
    262
    -0.06
     lately
    -0.06
    amak
    -0.06
    reece
    -0.06
    POSITIVE LOGITS
     ëĭ¹ìĭľ
    0.09
     tehdy
    0.08
     ÑĤогда
    0.07
    ειο
    0.07
    _NULL
    0.07
     ogl
    0.07
    ìĭľìĹIJ
    0.07
     ÙħÙĨÙĩ
    0.07
     vụ
    0.07
     ÄĮech
    0.07
    Activations Density 0.000%

    No Known Activations