© 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. 83324
    Prev
    Next
    INDEX
    Explanations

    references to local services and professionals available for hire

    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
    اÙĦÙĬا
    -0.08
     cest
    -0.07
     scand
    -0.07
    kube
    -0.07
    converter
    -0.07
    *pow
    -0.07
     اÙĦداخ
    -0.07
    Ú©ÙĪر
    -0.07
    Ñıб
    -0.07
    HeaderCode
    -0.06
    POSITIVE LOGITS
     who
    0.08
    enberg
    0.07
     whom
    0.07
     kteÅĻÃŃ
    0.07
     available
    0.07
     near
    0.07
    882
    0.07
    idd
    0.07
    alo
    0.06
     ratings
    0.06
    Activations Density 0.019%

    No Known Activations