© 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. 29955
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or code structure

    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
    CREMENT
    -0.07
    تÛĮب
    -0.07
    (/*
    -0.07
    .dsl
    -0.07
    PRINTF
    -0.07
     misd
    -0.07
    erness
    -0.07
     دÙĤÛĮ
    -0.06
    atik
    -0.06
    ignon
    -0.06
    POSITIVE LOGITS
     etc
    0.10
    etc
    0.09
     ÑĤоÑīо
    0.08
    resi
    0.06
    LastError
    0.06
     finally
    0.06
     ÙĪغÙĬر
    0.05
    hoa
    0.05
    orre
    0.05
    plant
    0.05
    Activations Density 0.085%

    No Known Activations