© 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. 80237
    Prev
    Next
    INDEX
    Explanations

    references to military honors and ceremonies

    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
    747
    -0.06
    ichi
    -0.06
     radar
    -0.06
    388
    -0.05
    èī
    -0.05
    ichel
    -0.05
     SWAT
    -0.05
    478
    -0.05
     kind
    -0.05
    832
    -0.05
    POSITIVE LOGITS
    zure
    0.08
    _LD
    0.07
    loh
    0.07
    ãĥ¼ãĤ¿
    0.07
    boru
    0.07
    ียà¸ļ
    0.07
    ignal
    0.07
    _subscribe
    0.07
    yclic
    0.07
    ziehung
    0.07
    Activations Density 0.001%

    No Known Activations