© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 71957
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and authority

    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
    itud
    -0.07
    è¨Ģãģ£ãģŁ
    -0.07
    arak
    -0.07
     Hogan
    -0.07
    éĻ½
    -0.07
    ichten
    -0.07
    ãĥ³ãĤ¹
    -0.07
    ouri
    -0.06
    (æľ¨
    -0.06
     ìķĦìĿ´ì½ĺ
    -0.06
    POSITIVE LOGITS
    inery
    0.07
     Persian
    0.07
    ingham
    0.06
    Iran
    0.06
    alie
    0.06
    wis
    0.06
     Iranian
    0.06
    ouncer
    0.06
    Indiana
    0.06
     Indiana
    0.06
    Activations Density 0.001%

    No Known Activations