© 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. 119648
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and notable names in a technical context

    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
    amba
    -0.06
    Äįka
    -0.06
    entions
    -0.06
     Guth
    -0.06
    áºŃn
    -0.06
     advantage
    -0.05
    INES
    -0.05
    ceae
    -0.05
    keterangan
    -0.05
    undle
    -0.05
    POSITIVE LOGITS
    mlin
    0.08
    statt
    0.07
    æ»
    0.07
    _Impl
    0.07
    arel
    0.07
    ÑĪив
    0.06
    etten
    0.06
    ulp
    0.06
    (factory
    0.06
     Harbor
    0.06
    Activations Density 0.001%

    No Known Activations