© 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. 128455
    Prev
    Next
    INDEX
    Explanations

    references to file system operations and related programming constructs

    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
    uer
    -0.07
    ж
    -0.06
    aeda
    -0.06
    né
    -0.06
     overt
    -0.06
    /setup
    -0.06
    shed
    -0.05
     Isl
    -0.05
    baum
    -0.05
    acr
    -0.05
    POSITIVE LOGITS
    à¹Ħร
    0.07
    оÑĢо
    0.07
    drv
    0.07
    ultipartFile
    0.07
    \/\/
    0.07
    ereco
    0.07
    ENTA
    0.07
    erca
    0.06
    //{{
    0.06
    ÃŃst
    0.06
    Activations Density 0.001%

    No Known Activations