© 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. 129886
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and 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
    imp
    -0.07
    Imp
    -0.07
     Imp
    -0.07
     imp
    -0.06
    ysa
    -0.06
    ondere
    -0.06
     corporate
    -0.06
    maal
    -0.06
    essel
    -0.05
    ond
    -0.05
    POSITIVE LOGITS
     Annunci
    0.08
    ovna
    0.07
    ÐĴС
    0.07
    peria
    0.07
    initWith
    0.07
    .dispose
    0.07
     pensar
    0.07
     nghá»ģ
    0.07
     Animalia
    0.07
    ÏĥÏĦα
    0.07
    Activations Density 0.024%

    No Known Activations