© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88166
    Prev
    Next
    INDEX
    Explanations

    terms related to vitamin deficiency and its implications for 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
    ryo
    -0.08
    кÑĥлÑı
    -0.07
     vrou
    -0.07
     áp
    -0.07
     infectious
    -0.07
    ĽĦ
    -0.06
     sleeves
    -0.06
    erties
    -0.06
    essor
    -0.06
    .epam
    -0.06
    POSITIVE LOGITS
     deficiency
    0.09
     deficient
    0.08
     deficiencies
    0.07
    ade
    0.07
     poor
    0.06
    æ¬ł
    0.06
     hol
    0.06
     Rib
    0.06
    USR
    0.06
     Magn
    0.06
    Activations Density 0.041%

    No Known Activations