© 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. 15-LLAMASCOPE-RES-131K
    11. 239
    Prev
    Next
    INDEX
    Explanations

    concepts related to athlete recovery and team 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
    æĻ´
    -0.07
     steroids
    -0.07
    Č↵
    -0.07
    FormGroup
    -0.06
    allenges
    -0.06
    iyle
    -0.06
    ÅŁt
    -0.06
    amba
    -0.06
     Hatch
    -0.06
    worksheet
    -0.06
    POSITIVE LOGITS
     Fat
    0.07
    fat
    0.07
     fat
    0.07
    Fat
    0.07
     fatigue
    0.07
    -fat
    0.07
    _REST
    0.07
    OND
    0.06
    imal
    0.06
    åĩ¡
    0.06
    Activations Density 0.018%

    No Known Activations