© 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. 108366
    Prev
    Next
    INDEX
    Explanations

    structural elements related to website navigation

    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
    owie
    -0.06
    wick
    -0.06
    anson
    -0.06
     Jensen
    -0.06
    enburg
    -0.05
     Kostenlose
    -0.05
     virgin
    -0.05
    ington
    -0.05
    ingham
    -0.05
    ба
    -0.05
    POSITIVE LOGITS
    تÙĪ
    0.08
    okers
    0.08
    ModelProperty
    0.08
    /TT
    0.07
    using
    0.07
    tesy
    0.07
    pig
    0.07
     Loy
    0.07
    ¢
    0.07
    /*č↵
    0.07
    Activations Density 0.001%

    No Known Activations