© 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. 104522
    Prev
    Next
    INDEX
    Explanations

    features related to relaxation and leisure facilities

    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
    kening
    -0.07
    thon
    -0.07
    ride
    -0.06
    æľ¯
    -0.06
    è¡ĵ
    -0.06
     wearer
    -0.06
    issippi
    -0.06
    å»ł
    -0.06
     wear
    -0.06
    stal
    -0.06
    POSITIVE LOGITS
    acie
    0.07
    .arm
    0.07
    enty
    0.07
     Fireplace
    0.06
    ISE
    0.06
    á»ĩn
    0.06
     Ø®ÙĪر
    0.06
     entertainment
    0.06
    SAT
    0.06
     oppos
    0.06
    Activations Density 0.014%

    No Known Activations