© 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. 15910
    Prev
    Next
    INDEX
    Explanations

    themes related to physical activity and energy management

    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
    umper
    -0.07
    angu
    -0.06
    caf
    -0.06
    otal
    -0.06
    alar
    -0.06
     perman
    -0.06
    umas
    -0.06
    chw
    -0.06
     Gest
    -0.06
    ÑĤÑı
    -0.06
    POSITIVE LOGITS
     tackling
    0.07
     tackles
    0.07
     productivity
    0.07
     performances
    0.07
     energy
    0.07
     performance
    0.07
     tackle
    0.07
    gebra
    0.06
     bodily
    0.06
    rames
    0.06
    Activations Density 0.025%

    No Known Activations