© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 90919
    Prev
    Next
    INDEX
    Explanations

    terms related to orthopedic medicine and surgical practices

    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
    Parcelable
    -0.09
    lys
    -0.08
    нÑıв
    -0.08
    eydi
    -0.07
    ãĢħ
    -0.07
    inese
    -0.07
    APON
    -0.07
    quire
    -0.07
    apy
    -0.07
    IXEL
    -0.07
    POSITIVE LOGITS
     joint
    0.09
     Emin
    0.07
     joints
    0.06
     Joint
    0.06
    joint
    0.06
    -related
    0.06
    oger
    0.06
    iddy
    0.06
     Damon
    0.06
    -FIRST
    0.06
    Activations Density 0.004%

    No Known Activations