© 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. 82848
    Prev
    Next
    INDEX
    Explanations

    inquiries and descriptions related to gardening and plant care

    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
     Bridges
    -0.06
     jane
    -0.06
     hall
    -0.06
    à¸ķร
    -0.06
     Jane
    -0.06
     fran
    -0.06
     delic
    -0.05
     suites
    -0.05
     appearing
    -0.05
     bridge
    -0.05
    POSITIVE LOGITS
    ioneer
    0.10
     addCriterion
    0.08
    Sharper
    0.07
     землÑı
    0.07
     огÑĢа
    0.07
    ibu
    0.07
    Experiment
    0.07
    âĻ¡
    0.07
    raquo
    0.07
    RTL
    0.07
    Activations Density 0.003%

    No Known Activations