© 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. 17-LLAMASCOPE-RES-131K
    11. 119900
    Prev
    Next
    INDEX
    Explanations

    terms related to the medical field

    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
    еÑģÑı
    -0.07
    lass
    -0.07
    ÙĪارÙĩ
    -0.07
     à¤¸à¤ľ
    -0.06
    iaux
    -0.06
    IAS
    -0.06
     Patrol
    -0.06
    ries
    -0.06
    ember
    -0.06
    otech
    -0.06
    POSITIVE LOGITS
    -grade
    0.08
    /math
    0.07
    /engine
    0.07
    rana
    0.07
    odge
    0.07
    ities
    0.07
    upe
    0.07
     anlamda
    0.07
    _registro
    0.07
    itate
    0.07
    Activations Density 0.018%

    No Known Activations