© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 58973
    Prev
    Next
    INDEX
    Explanations

    specific details and resources related to senior living and assistance

    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
     Summit
    -0.06
    64
    -0.06
     Kits
    -0.05
     Lionel
    -0.05
    urve
    -0.05
     spur
    -0.05
     folded
    -0.05
     Hastings
    -0.05
     Españ
    -0.05
     Diamond
    -0.05
    POSITIVE LOGITS
    /filter
    0.08
     platform
    0.08
    _FILTER
    0.08
    ÑĩиÑħ
    0.08
    iqu
    0.08
     aggregate
    0.07
    edn
    0.07
    Aggregate
    0.07
     FILTER
    0.07
     Aggregate
    0.07
    Activations Density 0.009%

    No Known Activations