© 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 EvalsExportsinterp-engineNEWAPI 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. 62539
    Prev
    Next
    INDEX
    Explanations

    code block structures and format in programming languages

    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
    imas
    -0.08
    imat
    -0.07
    gii
    -0.07
     بع
    -0.07
    icias
    -0.07
    igkeit
    -0.06
    ewis
    -0.06
    PROTO
    -0.06
    ãģĭãĤı
    -0.06
    ÏĢι
    -0.06
    POSITIVE LOGITS
     super
    0.09
    uper
    0.09
    super
    0.08
     InitializeComponent
    0.07
     initComponents
    0.06
    	super
    0.06
     ÙħØŃÙĦ
    0.06
    lege
    0.06
    .setSize
    0.06
    Super
    0.06
    Activations Density 0.004%

    No Known Activations