© 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. 15-LLAMASCOPE-RES-131K
    11. 88889
    Prev
    Next
    INDEX
    Explanations

    tokens related to programming syntax or code elements

    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
    οκ
    -0.07
    ysa
    -0.07
    bane
    -0.07
     Plain
    -0.07
    ifa
    -0.06
    anford
    -0.06
    ekl
    -0.06
    ys
    -0.06
    ags
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
    ANGLES
    0.07
    EMON
    0.06
    .INSTANCE
    0.06
     stat
    0.06
    InSection
    0.06
    íĻľ
    0.06
    à¸Ńส
    0.06
    ÙIJÙħ
    0.06
    âĢ¢↵↵
    0.06
    æ°Ķ
    0.06
    Activations Density 0.054%

    No Known Activations