Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43418
    Prev
    Next
    INDEX
    Explanations

    references to recovery and results from injuries or medical interventions

    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
    lier
    -0.08
    ies
    -0.08
    rost
    -0.08
    IES
    -0.07
    aggi
    -0.07
    ettle
    -0.07
    ae
    -0.06
    aging
    -0.06
    arto
    -0.06
    ota
    -0.06
    POSITIVE LOGITS
    _hostname
    0.07
     æij
    0.06
    ابÙĬ
    0.06
    obuf
    0.06
    zoom
    0.06
     Closed
    0.06
    _MACRO
    0.06
    channels
    0.06
     Developer
    0.06
    ÃĹ↵↵
    0.06
    Activations Density 0.003%

    No Known Activations