© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 88995
    Prev
    Next
    INDEX
    Explanations

    terms related to military aviation and fighter aircraft

    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
    ollapsed
    -0.08
     cancelButtonTitle
    -0.07
    egin
    -0.07
    SURE
    -0.07
    etu
    -0.07
    rå
    -0.07
    ÑĪиб
    -0.07
     Gür
    -0.07
    CastException
    -0.07
    itzer
    -0.06
    POSITIVE LOGITS
    fold
    0.06
    fan
    0.06
     escorts
    0.06
    640
    0.06
    /she
    0.06
     McGu
    0.06
    anford
    0.06
     Ellison
    0.06
    /light
    0.06
    ÅĻeb
    0.05
    Activations Density 0.008%

    No Known Activations