© 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. 61773
    Prev
    Next
    INDEX
    Explanations

    phrases that express necessity or obligation

    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
    ivot
    -0.08
    upp
    -0.08
    peare
    -0.08
    Å¡nÃŃ
    -0.07
    lez
    -0.07
     Deniz
    -0.07
     Mezi
    -0.07
     Currency
    -0.07
    onz
    -0.07
    .synthetic
    -0.07
    POSITIVE LOGITS
     must
    0.07
    must
    0.07
    n
    0.06
     Must
    0.06
    ahn
    0.06
    Must
    0.06
     somewhere
    0.06
     surely
    0.06
     either
    0.06
    uma
    0.06
    Activations Density 0.015%

    No Known Activations