© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 93763
    Prev
    Next
    INDEX
    Explanations

    programming syntax or structures

    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
    :UITableView
    -0.07
    _mapped
    -0.06
    о
    -0.06
    olson
    -0.06
    kie
    -0.06
    êµ´
    -0.06
    uben
    -0.06
    weed
    -0.06
    иÑĤелÑĮ
    -0.06
    raith
    -0.06
    POSITIVE LOGITS
     Byrne
    0.08
    afe
    0.07
     ----------------------------------------------------------------------↵
    0.07
    ุม
    0.07
    CLR
    0.07
    ارس
    0.07
    Moder
    0.07
    .messaging
    0.07
     caffe
    0.06
     Clarke
    0.06
    Activations Density 0.000%

    No Known Activations