© 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. 125604
    Prev
    Next
    INDEX
    Explanations

    references to government and organizational communication

    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
    bart
    -0.06
    å¼ı
    -0.06
    Ñĥд
    -0.06
    flashdata
    -0.06
     Mob
    -0.06
     crud
    -0.05
     Pas
    -0.05
     overs
    -0.05
    ud
    -0.05
     Wan
    -0.05
    POSITIVE LOGITS
     aray
    0.07
    ussy
    0.07
     merak
    0.07
    ůst
    0.07
     ontvangst
    0.07
    ανά
    0.07
    XHR
    0.06
    unnable
    0.06
    ataset
    0.06
    κι
    0.06
    Activations Density 0.002%

    No Known Activations