© 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. 17-LLAMASCOPE-RES-131K
    11. 40049
    Prev
    Next
    INDEX
    Explanations

    words related to physical injuries or discomfort

    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
     inval
    -0.08
    opi
    -0.08
    身ä¸Ĭ
    -0.07
    allis
    -0.07
     дÑĥÑĪ
    -0.07
    é¼»
    -0.07
    imiz
    -0.07
    inati
    -0.06
    xfff
    -0.06
     chin
    -0.06
    POSITIVE LOGITS
     lan
    0.06
     function
    0.06
     bud
    0.06
    esz
    0.06
    /body
    0.06
     Cunningham
    0.06
     Tah
    0.06
     cavity
    0.06
    /right
    0.06
     functioning
    0.05
    Activations Density 0.048%

    No Known Activations