© 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. 15355
    Prev
    Next
    INDEX
    Explanations

    information about the usage and effects of medications or supplements

    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
    одо
    -0.08
    ikel
    -0.06
    ÑĢÑĥÑĩ
    -0.06
     antibiotics
    -0.06
    adele
    -0.06
    rub
    -0.06
    ICollection
    -0.06
    ometr
    -0.06
     artificially
    -0.06
    боÑĢ
    -0.06
    POSITIVE LOGITS
     dosage
    0.13
     dos
    0.13
     doses
    0.12
    dos
    0.11
     dose
    0.10
     доз
    0.10
     Dos
    0.09
    Dos
    0.09
    åīĤ
    0.07
     das
    0.07
    Activations Density 0.046%

    No Known Activations