© 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. 128848
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "surrounding" or "enclosing" within a context

    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
    ibs
    -0.07
     пÑĢоÑĤивоп
    -0.06
    UiThread
    -0.06
    ë´ī
    -0.06
    reeze
    -0.06
     Runnable
    -0.06
    sek
    -0.06
    ibrate
    -0.06
    ANNER
    -0.06
    imal
    -0.06
    POSITIVE LOGITS
    roud
    0.07
    reta
    0.06
     RouterModule
    0.06
     æĦ
    0.06
     $č↵
    0.06
    -Core
    0.06
    รà¸Ńà¸ļ
    0.06
     вокÑĢÑĥг
    0.06
     ankles
    0.06
    legg
    0.06
    Activations Density 0.024%

    No Known Activations