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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 60610
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to events or schedules

    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
    clide
    -0.07
    ieee
    -0.07
    oplayer
    -0.07
    rint
    -0.07
    iaz
    -0.07
    ynet
    -0.06
    olet
    -0.06
    IEWS
    -0.06
     æ¯
    -0.06
    asper
    -0.06
    POSITIVE LOGITS
     Gilles
    0.06
    ýš
    0.06
    ease
    0.06
    zsche
    0.06
     Rena
    0.06
    à¸Ĩ
    0.06
    ìĹ°
    0.06
     Sox
    0.06
     Mechan
    0.05
    à¹Ģà¸ĩ
    0.05
    Activations Density 0.001%

    No Known Activations