© 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. 84709
    Prev
    Next
    INDEX
    Explanations

    references to military vehicles and equipment

    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
    usz
    -0.08
    abei
    -0.07
    .defaultValue
    -0.07
    รà¸ĸ
    -0.07
     crit
    -0.07
    gan
    -0.06
    lain
    -0.06
    огод
    -0.06
     veh
    -0.06
    /Internal
    -0.06
    POSITIVE LOGITS
     operated
    0.07
    /table
    0.07
    pository
    0.06
     confiscated
    0.06
     owners
    0.06
     manufacturer
    0.06
     Coalition
    0.06
    ito
    0.06
     owner
    0.06
    zik
    0.06
    Activations Density 0.074%

    No Known Activations