© 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. 107928
    Prev
    Next
    INDEX
    Explanations

    references to foreign keys in database structures

    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
    oppers
    -0.08
     wed
    -0.08
    ãİ¡
    -0.07
     Türkçe
    -0.07
    -mouth
    -0.07
    ares
    -0.07
    _simps
    -0.07
    gency
    -0.07
    .want
    -0.07
    mpl
    -0.07
    POSITIVE LOGITS
     Bill
    0.06
    ManyToOne
    0.06
     tent
    0.05
    upert
    0.05
    /link
    0.05
    /reference
    0.05
     defer
    0.05
     foreign
    0.05
    ive
    0.05
    )index
    0.05
    Activations Density 0.002%

    No Known Activations