© 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. 83468
    Prev
    Next
    INDEX
    Explanations

    phrases related to health, research, and the evaluation of studies or interventions

    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
    .heroku
    -0.07
    NOP
    -0.07
    .Interop
    -0.06
     Ïį
    -0.06
    HEME
    -0.06
    Ñľ
    -0.06
    ÑĽ
    -0.06
    знаÑĩа
    -0.06
    rimon
    -0.06
    RestController
    -0.06
    POSITIVE LOGITS
     needs
    0.13
     future
    0.13
     Needs
    0.12
     should
    0.11
     need
    0.11
    Needs
    0.10
    needs
    0.10
     ought
    0.10
     Future
    0.10
     could
    0.10
    Activations Density 0.158%

    No Known Activations