© 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. 28619
    Prev
    Next
    INDEX
    Explanations

    programming-related language constructs and access modifiers

    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
    .scalablytyped
    -0.08
    iqueta
    -0.08
     ÐľÑĸнÑĸÑģÑĤ
    -0.08
    usher
    -0.07
    inker
    -0.07
    ivicrm
    -0.07
    pler
    -0.07
     BitConverter
    -0.07
    ÑģÑĤиÑĤÑĥ
    -0.07
    /tutorial
    -0.07
    POSITIVE LOGITS
     copy
    0.07
     fluid
    0.07
     cogn
    0.07
     void
    0.06
     cloning
    0.06
     Copy
    0.06
     clone
    0.06
    0.06
    -fluid
    0.06
    733
    0.06
    Activations Density 0.000%

    No Known Activations