© 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 EvalsExportsAPI 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. 58620
    Prev
    Next
    INDEX
    Explanations

    roles and titles related to political and administrative positions

    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
    utenberg
    -0.08
    sburg
    -0.07
    ritz
    -0.07
    drop
    -0.07
    еÑĪ
    -0.07
     drop
    -0.07
    è¯Ŀ
    -0.07
    -drop
    -0.07
    ioni
    -0.07
     reli
    -0.07
    POSITIVE LOGITS
     briefly
    0.08
     Brief
    0.07
     resignation
    0.07
     resign
    0.07
     appointment
    0.07
     brief
    0.07
     %[
    0.06
     twice
    0.06
    amac
    0.06
    brief
    0.06
    Activations Density 0.024%

    No Known Activations