© 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. 117969
    Prev
    Next
    INDEX
    Explanations

    concepts related to physical tension and joint health

    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
    åĤ¬
    -0.07
     yans
    -0.06
     Kaplan
    -0.06
    odate
    -0.06
     Kostenlose
    -0.06
    Ïģιά
    -0.06
    affe
    -0.06
    uish
    -0.06
    phinx
    -0.06
     FileNotFoundError
    -0.06
    POSITIVE LOGITS
     strain
    0.09
     strains
    0.08
     stress
    0.07
     Stress
    0.07
     stresses
    0.07
    923
    0.07
     joints
    0.07
     pressure
    0.07
     Pressure
    0.07
    stress
    0.06
    Activations Density 0.003%

    No Known Activations