© 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. 5277
    Prev
    Next
    INDEX
    Explanations

    references to Donald Trump and associated political 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
    zza
    -0.07
    EXPORT
    -0.07
    vale
    -0.07
    ارÙģ
    -0.06
    afka
    -0.06
    à¥ģà¤Ń
    -0.06
    SYM
    -0.06
     бÑĢоÑģ
    -0.06
     подв
    -0.06
    eltas
    -0.06
    POSITIVE LOGITS
    177
    0.06
     Palm
    0.06
    ivan
    0.06
    akah
    0.06
    HV
    0.05
     Aires
    0.05
    aspers
    0.05
    XR
    0.05
    unos
    0.05
    .Strict
    0.05
    Activations Density 0.003%

    No Known Activations