© 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. 121173
    Prev
    Next
    INDEX
    Explanations

    discussions related to military equipment and its repairability

    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
     fractional
    -0.07
    æŀª
    -0.07
     Orr
    -0.07
    culo
    -0.06
    Bindings
    -0.06
     Brake
    -0.06
     SWAT
    -0.06
    azio
    -0.06
    planet
    -0.06
    flux
    -0.06
    POSITIVE LOGITS
     capabilities
    0.07
     older
    0.07
    /gif
    0.06
    볨
    0.06
     Liberties
    0.06
    loon
    0.06
     launch
    0.06
    æ£ĭ
    0.06
    ifik
    0.06
    ëŁī
    0.06
    Activations Density 0.021%

    No Known Activations