© 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. 107264
    Prev
    Next
    INDEX
    Explanations

    quantitative statistics and demographic information about a population

    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
    bbe
    -0.07
    apur
    -0.07
    пеÑĩ
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    loth
    -0.07
    _macros
    -0.07
     ä¸ļ
    -0.07
     wyn
    -0.07
    aks
    -0.07
    ede
    -0.06
    POSITIVE LOGITS
    issan
    0.06
    ilver
    0.06
    ersh
    0.06
    gli
    0.06
    rama
    0.06
    ought
    0.06
     Sutton
    0.05
    impl
    0.05
    adio
    0.05
    apons
    0.05
    Activations Density 0.003%

    No Known Activations