© 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. 71187
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax 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
    alama
    -0.06
    odable
    -0.06
    ulet
    -0.05
     bitte
    -0.05
    odium
    -0.05
    /rfc
    -0.05
    evi
    -0.05
     Colt
    -0.05
     Allison
    -0.05
    ennie
    -0.05
    POSITIVE LOGITS
    à¤¾à¤ł
    0.07
    ÙĥÙĬÙĦ
    0.07
    æĢĢ
    0.07
    /or
    0.07
     bay
    0.06
    opsy
    0.06
    ãĥ©ãĤ¯
    0.06
    ãĥŃãĥ³
    0.06
     zab
    0.06
    annes
    0.06
    Activations Density 0.001%

    No Known Activations