© 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. 73999
    Prev
    Next
    INDEX
    Explanations

    references to caregivers and their roles

    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
    uffer
    -0.08
    ixin
    -0.08
    ủ
    -0.07
    kie
    -0.07
    quito
    -0.07
    že
    -0.07
    mann
    -0.07
    anian
    -0.07
    orf
    -0.07
    outu
    -0.07
    POSITIVE LOGITS
    ship
    0.08
    hip
    0.07
     duty
    0.07
    tsky
    0.07
    iesel
    0.07
    eral
    0.06
    SHIP
    0.06
     responsibilities
    0.06
    ves
    0.06
    Ship
    0.06
    Activations Density 0.003%

    No Known Activations