© 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. 9-LLAMASCOPE-RES-131K
    11. 96503
    Prev
    Next
    INDEX
    Explanations

    occurrences of non-alphanumeric text elements such as mathematical symbols and special characters

    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
    mes
    -0.07
    ette
    -0.07
    NgModule
    -0.06
    ãĥĨãĥ«
    -0.06
    istes
    -0.06
    士
    -0.06
    abad
    -0.06
    æĻ®
    -0.06
    chyb
    -0.06
    uld
    -0.06
    POSITIVE LOGITS
    ĥn
    0.07
    azer
    0.07
    dio
    0.06
    scal
    0.06
    Notifier
    0.06
    qv
    0.06
    tility
    0.06
     Quart
    0.06
    089
    0.06
    ellen
    0.06
    Activations Density 0.008%

    No Known Activations