© 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. 87029
    Prev
    Next
    INDEX
    Explanations

    phrases related to inspiration and aspirational goals

    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
    atism
    -0.08
    isman
    -0.07
    ÑĢан
    -0.07
    جد
    -0.07
    ombs
    -0.07
    ãĤīãģļ
    -0.07
    ĨĴ
    -0.07
     gratuits
    -0.07
    å¹
    -0.07
    ......↵↵
    -0.07
    POSITIVE LOGITS
     a
    0.08
     an
    0.07
     the
    0.06
     quite
    0.06
     very
    0.06
    sembled
    0.06
     fairly
    0.05
     industry
    0.05
    avia
    0.05
     watering
    0.05
    Activations Density 0.023%

    No Known Activations