© 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. 17-LLAMASCOPE-RES-131K
    11. 71641
    Prev
    Next
    INDEX
    Explanations

    concepts related to long-term sustainability and cultural initiatives in the arts

    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
    onga
    -0.07
    oku
    -0.06
    æ®ĭ
    -0.06
    175
    -0.06
    Division
    -0.06
     Tune
    -0.06
     Comple
    -0.06
     Dr
    -0.06
     guy
    -0.06
     Division
    -0.06
    POSITIVE LOGITS
    iming
    0.08
     ziy
    0.07
    InputDialog
    0.07
    lds
    0.07
     Kuzey
    0.07
     молод
    0.07
    _parm
    0.06
    saldo
    0.06
    visa
    0.06
    Verdana
    0.06
    Activations Density 0.019%

    No Known Activations