© 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. 15558
    Prev
    Next
    INDEX
    Explanations

    phrases related to health implications and their discussions

    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
     dán
    -0.07
    iola
    -0.07
    GLE
    -0.07
    gle
    -0.07
     Vz
    -0.07
    "+"
    -0.07
     taraf
    -0.07
     proje
    -0.07
    atts
    -0.07
    -Za
    -0.07
    POSITIVE LOGITS
    sembl
    0.07
    rection
    0.06
    ourke
    0.06
    igi
    0.06
    asar
    0.06
    quisition
    0.06
    dden
    0.06
    .bootstrapcdn
    0.06
    wner
    0.06
    tober
    0.06
    Activations Density 1.406%

    No Known Activations