© 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. 107450
    Prev
    Next
    INDEX
    Explanations

    phrases relating to legal terms and commitments

    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
    olini
    -0.08
    ITS
    -0.07
    ernel
    -0.07
     nameLabel
    -0.07
    olean
    -0.07
    peg
    -0.07
     Higgins
    -0.07
    chwitz
    -0.07
    PTR
    -0.07
    @brief
    -0.07
    POSITIVE LOGITS
    yon
    0.06
    áme
    0.06
    swick
    0.06
    eros
    0.06
    arella
    0.06
     rats
    0.05
    ungeon
    0.05
     unknown
    0.05
     double
    0.05
    /plugins
    0.05
    Activations Density 0.004%

    No Known Activations