© 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. 54471
    Prev
    Next
    INDEX
    Explanations

    phrases related to event planning and organization

    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
     resc
    -0.07
    ìĬ¹
    -0.06
    loser
    -0.06
    /max
    -0.06
     pair
    -0.06
    ä¼´
    -0.06
     accompanies
    -0.06
     accompany
    -0.06
    еÑĢÑĪ
    -0.06
    Contours
    -0.06
    POSITIVE LOGITS
     SetUp
    0.07
    onet
    0.07
    setup
    0.07
     setup
    0.07
     Setup
    0.07
    aurus
    0.07
    rum
    0.07
    egin
    0.07
    ilis
    0.07
     preparations
    0.06
    Activations Density 0.025%

    No Known Activations