© 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. 38635
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to patent applications

    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
    unic
    -0.06
     hug
    -0.06
    ovich
    -0.06
    å¦ĥ
    -0.06
    виж
    -0.06
     sweetheart
    -0.06
     à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    -0.06
    iron
    -0.06
     gigs
    -0.06
     buck
    -0.06
    POSITIVE LOGITS
    岸
    0.07
    ENTE
    0.07
    ContentPane
    0.07
    entes
    0.06
     Moran
    0.06
    chod
    0.06
    é¦
    0.06
     ì´Ī
    0.06
    /language
    0.06
    رÙĬد
    0.06
    Activations Density 0.007%

    No Known Activations