© 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. 125617
    Prev
    Next
    INDEX
    Explanations

    terms related to access and expertise 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
     NDEBUG
    -0.07
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.07
     Impress
    -0.07
    .DropDown
    -0.07
    lsa
    -0.07
    codec
    -0.07
    ì¹
    -0.07
    á»Ńi
    -0.07
    رÙĪز
    -0.07
    tright
    -0.07
    POSITIVE LOGITS
     said
    0.07
    enthal
    0.06
     sources
    0.06
    ublish
    0.06
     Anonymous
    0.06
     but
    0.06
     Sources
    0.06
     sheet
    0.06
    Sources
    0.06
    pies
    0.05
    Activations Density 0.001%

    No Known Activations