© 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. 27301
    Prev
    Next
    INDEX
    Explanations

    achievements and accolades in academic and athletic contexts

    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
    ковоÑĹ
    -0.07
    ingroup
    -0.07
     efekt
    -0.07
    å»
    -0.06
    rouch
    -0.06
     Tie
    -0.06
     dá
    -0.06
    ãĥ³ãĥĨãĤ£
    -0.06
    (disposing
    -0.06
    orce
    -0.06
    POSITIVE LOGITS
     Cocoa
    0.07
    âĢ¦↵↵↵
    0.06
    innie
    0.06
    elik
    0.06
    ä¸Ģå¹´
    0.06
    480
    0.06
    ÂĿ
    0.06
    ENARIO
    0.06
    ocz
    0.06
    âĢ
    0.06
    Activations Density 0.018%

    No Known Activations