© 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. 3137
    Prev
    Next
    INDEX
    Explanations

    references to childcare-related topics and qualifications

    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
    éĺħ读次æķ°
    -0.11
     знов
    -0.10
     putas
    -0.09
    using
    -0.09
    ulumi
    -0.09
    çĽijåIJ¬é¡µéĿ¢
    -0.09
    _mA
    -0.09
    engeance
    -0.09
    gua
    -0.09
    _mC
    -0.09
    POSITIVE LOGITS
    0.08
    .
    0.07
     its
    0.07
     than
    0.07
     it
    0.07
    Âł
    0.06
     &
    0.06
    )
    0.06
     which
    0.06
     same
    0.06
    Activations Density 1.672%

    No Known Activations