© 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. 59699
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities and new beginnings

    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
    umbing
    -0.07
    isel
    -0.06
     maturity
    -0.06
    inish
    -0.06
    OMPI
    -0.06
    ç®
    -0.06
    lew
    -0.06
    jer
    -0.06
    .SaveChanges
    -0.06
    ripp
    -0.06
    POSITIVE LOGITS
     new
    0.21
    new
    0.16
    -new
    0.15
     NEW
    0.15
    æĸ°
    0.15
     æĸ°
    0.15
    æĸ°çļĦ
    0.14
     новÑĭÑħ
    0.14
    .new
    0.14
    /new
    0.14
    Activations Density 0.067%

    No Known Activations