© 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. 77623
    Prev
    Next
    INDEX
    Explanations

    expressions related to energy levels and physical capabilities

    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
    ñana
    -0.06
    eldon
    -0.06
    pson
    -0.06
     Singleton
    -0.06
    ongyang
    -0.06
    349
    -0.06
    ipes
    -0.06
    283
    -0.06
    _refl
    -0.06
    ÑĩаÑĤ
    -0.06
    POSITIVE LOGITS
     normal
    0.08
     activities
    0.08
    esser
    0.07
     competitive
    0.07
     independence
    0.07
     physical
    0.07
    competitive
    0.07
     participation
    0.07
     activity
    0.06
    ocker
    0.06
    Activations Density 0.010%

    No Known Activations