© 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 EvalsExportsinterp-engineNEWAPI 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. 61878
    Prev
    Next
    INDEX
    Explanations

    terms related to support and care for animals and patients

    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
    aeda
    -0.07
    ombre
    -0.07
    neau
    -0.07
    asher
    -0.07
    Looper
    -0.07
    ÑģеÑĢ
    -0.07
    eyse
    -0.06
    éŀ
    -0.06
    /weather
    -0.06
    urope
    -0.06
    POSITIVE LOGITS
     support
    0.07
     SUPPORT
    0.07
     Dahl
    0.07
    support
    0.06
    -support
    0.06
     flatt
    0.06
     Support
    0.06
     pressing
    0.06
    rah
    0.06
    å¾
    0.06
    Activations Density 0.003%

    No Known Activations