© 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 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. 16381
    Prev
    Next
    INDEX
    Explanations

    references to printing services and contract management

    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
    aticon
    -0.07
    actable
    -0.07
    instein
    -0.06
    agrid
    -0.06
    _ENTRY
    -0.06
    _rc
    -0.06
    Extern
    -0.06
    ãĤ¹ãĤ«
    -0.06
     Courtesy
    -0.06
     Manuals
    -0.06
    POSITIVE LOGITS
     printing
    0.10
     Printing
    0.09
    Printing
    0.08
     print
    0.08
     Print
    0.08
    -print
    0.07
    INK
    0.07
     printers
    0.07
     orders
    0.07
     production
    0.07
    Activations Density 0.009%

    No Known Activations