© 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. 73397
    Prev
    Next
    INDEX
    Explanations

    references to network protocols and internet-related terminology

    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
    umps
    -0.07
    idel
    -0.07
    uely
    -0.07
    igli
    -0.06
     pump
    -0.06
    itat
    -0.06
    ao
    -0.06
    itta
    -0.06
    -One
    -0.06
    489
    -0.06
    POSITIVE LOGITS
     molec
    0.07
     resid
    0.06
    IFORM
    0.06
    enga
    0.06
    ãĤ¤ãĥĪ
    0.06
     Manga
    0.06
    æ´¥
    0.06
     ÙģرÙĪدگاÙĩ
    0.06
     varsa
    0.06
    ERO
    0.06
    Activations Density 0.001%

    No Known Activations