© 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. 42023
    Prev
    Next
    INDEX
    Explanations

    references to various programs, initiatives, and collaborations in education and community development 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
    urve
    -0.07
    Ãłu
    -0.06
     cái
    -0.06
    itler
    -0.06
    antity
    -0.06
    ãĤ¤ãĤ¹
    -0.06
    egie
    -0.06
    metics
    -0.06
    ruit
    -0.06
    ãĤ¢ãĥ¼
    -0.06
    POSITIVE LOGITS
     initiative
    0.09
    848
    0.08
    esh
    0.08
     series
    0.07
    ims
    0.07
    init
    0.07
     program
    0.07
    pto
    0.07
    oux
    0.07
     platform
    0.07
    Activations Density 0.039%

    No Known Activations