© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 99155
    Prev
    Next
    INDEX
    Explanations

    terms related to parks and recreation activities or departments

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    anou
    -0.06
    UBLE
    -0.06
    sburg
    -0.06
    ané
    -0.06
    uble
    -0.06
    chter
    -0.06
     Harper
    -0.06
    APSHOT
    -0.06
    ÃŃcÃŃ
    -0.06
    >Returns
    -0.06
    POSITIVE LOGITS
    Advertisement
    0.06
    ltra
    0.06
    turnstile
    0.06
    íĻľ
    0.06
    land
    0.06
    ynth
    0.06
    logan
    0.06
     Customer
    0.06
     Suff
    0.06
     Contr
    0.06
    Activations Density 0.005%

    No Known Activations