© 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 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. 77139
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to nature and its preservation

    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
    ulu
    -0.08
    eping
    -0.07
    acific
    -0.07
     DeepCopy
    -0.07
    åŃĿ
    -0.06
    Å¡ÃŃ
    -0.06
    γοÏģ
    -0.06
    (æĹ¥
    -0.06
    eon
    -0.06
    ÑģÑĤи
    -0.06
    POSITIVE LOGITS
     beauty
    0.07
     wealth
    0.07
     Ga
    0.06
     Jewel
    0.06
    rack
    0.06
     resources
    0.06
    çij
    0.06
    letcher
    0.06
     stepping
    0.06
     Tape
    0.06
    Activations Density 0.008%

    No Known Activations