© 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. 77249
    Prev
    Next
    INDEX
    Explanations

    references to monetary amounts or financial figures

    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
    ourg
    -0.06
    ÑĪка
    -0.06
    3
    -0.06
     Beste
    -0.06
     localtime
    -0.05
     Staples
    -0.05
    WM
    -0.05
    gon
    -0.05
    nen
    -0.05
     jack
    -0.05
    POSITIVE LOGITS
    erre
    0.08
    cctor
    0.07
    chandle
    0.07
    iVar
    0.07
    uppe
    0.07
    leftright
    0.07
    erin
    0.07
    à¹Īาà¸ķ
    0.07
    achts
    0.07
    ÑģÑĮ
    0.06
    Activations Density 0.000%

    No Known Activations