© 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 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. 85839
    Prev
    Next
    INDEX
    Explanations

    references to awards, nominations, or notable entities in various contexts

    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
    ÅĻet
    -0.06
    anas
    -0.06
    223
    -0.06
    ugas
    -0.06
    ellen
    -0.06
    ql
    -0.06
     margins
    -0.06
    estr
    -0.06
     _
    -0.05
    ada
    -0.05
    POSITIVE LOGITS
     меÑħ
    0.09
    ecast
    0.08
    :;↵
    0.07
    æŀĿ
    0.07
    اکÛĮ
    0.07
    epam
    0.07
    _erase
    0.07
    fone
    0.07
    gebn
    0.07
    UsageId
    0.07
    Activations Density 0.000%

    No Known Activations