© 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. 123838
    Prev
    Next
    INDEX
    Explanations

    references to medical examinations and procedures

    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
    è¥
    -0.08
     plasma
    -0.06
    ammer
    -0.06
     Mans
    -0.06
    wers
    -0.06
    asma
    -0.06
    lemn
    -0.06
    ucceed
    -0.06
     Demir
    -0.06
     Concrete
    -0.05
    POSITIVE LOGITS
    usk
    0.07
    tÃŃ
    0.06
    raz
    0.06
    æĿī
    0.06
    füh
    0.06
    eneg
    0.06
    rez
    0.06
     semiclass
    0.06
    _PENDING
    0.06
    testdata
    0.06
    Activations Density 0.003%

    No Known Activations