© 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. 9-LLAMASCOPE-RES-131K
    11. 95246
    Prev
    Next
    INDEX
    Explanations

    terms related to wastewater management and treatment 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
    opher
    -0.06
    ãĥ¼ãĥį
    -0.06
    atra
    -0.06
     rehears
    -0.06
    agara
    -0.06
    otine
    -0.06
     Pell
    -0.06
     Ping
    -0.06
    usc
    -0.06
    nev
    -0.06
    POSITIVE LOGITS
     facility
    0.07
    æ½®
    0.07
    anson
    0.07
    ÏģÏİν
    0.07
    -www
    0.07
    /process
    0.07
     Facility
    0.07
    urator
    0.07
    ãĥ¼ãĥĹ
    0.07
    (PHP
    0.07
    Activations Density 0.005%

    No Known Activations