© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98500
    Prev
    Next
    INDEX
    Explanations

    syntactical structures and patterns involving template parameters in code

    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
    onta
    -0.06
    igy
    -0.06
     Miss
    -0.06
    eft
    -0.06
    kuk
    -0.06
     Sey
    -0.06
    erdale
    -0.06
    )prepare
    -0.06
    erin
    -0.06
    phis
    -0.06
    POSITIVE LOGITS
    -strip
    0.07
     náz
    0.06
    ugal
    0.06
    ırak
    0.06
    benh
    0.06
    ä¸ĺ
    0.06
    ERRU
    0.06
    tras
    0.06
     breadcrumb
    0.06
    ChangedEventArgs
    0.06
    Activations Density 0.014%

    No Known Activations