© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83285
    Prev
    Next
    INDEX
    Explanations

    terms related to sustainability and environmental initiatives

    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
     Wein
    -0.07
    inan
    -0.07
     boca
    -0.07
    ÑĢазÑĥ
    -0.07
    rossover
    -0.06
    ocks
    -0.06
    ftware
    -0.06
    елеÑĦ
    -0.06
    imuth
    -0.06
    ERP
    -0.06
    POSITIVE LOGITS
    ingt
    0.07
    /stretch
    0.06
    ungi
    0.06
    ัวร
    0.06
    jis
    0.06
     delta
    0.06
     impro
    0.06
     bananas
    0.06
    esk
    0.06
     accompagn
    0.06
    Activations Density 0.013%

    No Known Activations