© 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. 88668
    Prev
    Next
    INDEX
    Explanations

    references to military aviation and aircraft specifications

    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
    adh
    -0.06
     heat
    -0.06
     ignition
    -0.06
     traction
    -0.06
    нение
    -0.06
     raz
    -0.06
    olta
    -0.05
    nv
    -0.05
     Heat
    -0.05
     ladder
    -0.05
    POSITIVE LOGITS
     feeding
    0.08
     refill
    0.08
     pouring
    0.08
     gravity
    0.08
    .feed
    0.08
     Äijá»ķ
    0.08
     filling
    0.08
     Fill
    0.08
    Fill
    0.08
     drops
    0.08
    Activations Density 0.116%

    No Known Activations