© 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. 87685
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Bolsonaro"

    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
    sez
    -0.08
     Stat
    -0.07
    teil
    -0.07
    otron
    -0.07
    byn
    -0.07
    /product
    -0.06
    smouth
    -0.06
    quez
    -0.06
    utan
    -0.06
     Lor
    -0.06
    POSITIVE LOGITS
     mes
    0.07
    _mes
    0.06
    raph
    0.06
    ilit
    0.06
    ancia
    0.06
     retreated
    0.06
     Clar
    0.06
     ########.
    0.06
    egr
    0.06
    allet
    0.06
    Activations Density 0.000%

    No Known Activations