© 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. 62207
    Prev
    Next
    INDEX
    Explanations

    terms related to skeletal injuries and their treatment

    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
    .nodeType
    -0.06
    IFO
    -0.06
    grave
    -0.06
     Cutter
    -0.06
    storage
    -0.06
     zby
    -0.06
     guts
    -0.06
    Aspect
    -0.06
    fol
    -0.06
    NCY
    -0.06
    POSITIVE LOGITS
     bones
    0.11
     bone
    0.11
     Bones
    0.10
     fracture
    0.10
     Bone
    0.10
    骨
    0.09
     oste
    0.09
    Bone
    0.09
     fractures
    0.09
     healing
    0.08
    Activations Density 0.028%

    No Known Activations