© 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. 107888
    Prev
    Next
    INDEX
    Explanations

    references to herbal remedies 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
    457
    -0.07
    Å¡en
    -0.07
     (?)
    -0.06
    ije
    -0.06
    ade
    -0.06
    _traits
    -0.06
    .states
    -0.06
    908
    -0.05
    geois
    -0.05
    89
    -0.05
    POSITIVE LOGITS
     Vs
    0.08
    одÑĥ
    0.08
    ména
    0.08
    ekli
    0.07
    usch
    0.07
    _drv
    0.07
     सद
    0.07
    odore
    0.07
    ↵
    0.07
    ç´ł
    0.07
    Activations Density 0.032%

    No Known Activations