© 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. 1788
    Prev
    Next
    INDEX
    Explanations

    technical terms related to compressed air systems and their applications in repair facilities

    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
     Maher
    -0.07
    _ctxt
    -0.07
    vetica
    -0.07
    æ£ļ
    -0.07
    .ai
    -0.06
    azio
    -0.06
    æī£
    -0.06
     scand
    -0.06
     atol
    -0.06
     mechanically
    -0.06
    POSITIVE LOGITS
     press
    0.08
    endale
    0.08
    olec
    0.08
     oil
    0.08
     pressure
    0.08
     pressures
    0.07
    -pressure
    0.07
     Fluid
    0.07
     Toro
    0.07
    pressure
    0.07
    Activations Density 0.011%

    No Known Activations