© 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. 9-LLAMASCOPE-RES-131K
    11. 97343
    Prev
    Next
    INDEX
    Explanations

    references to document-related actions or elements

    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
    zdy
    -0.07
    ante
    -0.07
    olver
    -0.07
    öst
    -0.07
    iant
    -0.07
    nar
    -0.07
    ocular
    -0.07
    onia
    -0.07
    sı
    -0.07
    ivot
    -0.06
    POSITIVE LOGITS
    olis
    0.06
    Subviews
    0.06
    intros
    0.06
    kh
    0.06
    ç´
    0.06
    ukt
    0.06
    agua
    0.06
    mare
    0.06
    itty
    0.06
     Garner
    0.05
    Activations Density 0.001%

    No Known Activations