© 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. 28999
    Prev
    Next
    INDEX
    Explanations

    terms related to waste management and garbage disposal

    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
    647
    -0.07
    .origin
    -0.07
    etto
    -0.07
     pragma
    -0.07
    avid
    -0.06
    風
    -0.06
    allet
    -0.06
    owi
    -0.06
    enu
    -0.06
    xic
    -0.06
    POSITIVE LOGITS
    /errors
    0.07
     Mou
    0.07
    .tie
    0.06
    ยะ
    0.06
    çķ
    0.06
    imulator
    0.06
     Vance
    0.06
     management
    0.06
     Nev
    0.06
    iode
    0.06
    Activations Density 0.003%

    No Known Activations