© 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. 39199
    Prev
    Next
    INDEX
    Explanations

    terms related to joint movement and physical rehabilitation

    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
    vor
    -0.07
    rors
    -0.07
    leta
    -0.06
    мон
    -0.06
    rier
    -0.06
    elog
    -0.06
    avigator
    -0.06
    bject
    -0.06
    ATUS
    -0.06
    RESS
    -0.06
    POSITIVE LOGITS
     mobility
    0.10
     joint
    0.10
     Mobility
    0.09
     joints
    0.09
    joint
    0.08
     movements
    0.08
     Joint
    0.08
    Joint
    0.07
     hinge
    0.07
    å¬
    0.07
    Activations Density 0.019%

    No Known Activations