© 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. 83725
    Prev
    Next
    INDEX
    Explanations

    terms related to psychological and physical concepts in the context of performance and embodiment

    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
    iae
    -0.07
    affen
    -0.07
    ollah
    -0.06
    æ¿
    -0.06
     recharge
    -0.06
    dash
    -0.06
    ifu
    -0.06
    lez
    -0.06
     Kou
    -0.06
    zelf
    -0.06
    POSITIVE LOGITS
     Blocking
    0.07
     diagrams
    0.06
     Diagram
    0.06
    aklı
    0.06
     diagram
    0.06
     dynamics
    0.06
     Blocked
    0.06
    raph
    0.06
    ignon
    0.06
    adia
    0.06
    Activations Density 0.001%

    No Known Activations