© 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. 15-LLAMASCOPE-RES-131K
    11. 86635
    Prev
    Next
    INDEX
    Explanations

    phrases related to probiotic products and their health benefits

    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
    erp
    -0.07
     chemicals
    -0.06
    911
    -0.06
    radu
    -0.06
     eos
    -0.06
     opioids
    -0.06
     draft
    -0.06
    762
    -0.06
    458
    -0.06
    /project
    -0.06
    POSITIVE LOGITS
    á¿ĸ
    0.06
     proven
    0.06
    ÙĦاÙģ
    0.06
    amping
    0.06
     Raz
    0.06
    TECTED
    0.06
    iÅŁim
    0.06
    .synthetic
    0.06
    ثار
    0.06
     trace
    0.06
    Activations Density 0.012%

    No Known Activations