© 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 EvalsExportsAPI 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. 130269
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to exceptions or restrictions

    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
    vid
    -0.07
    ä¸į足
    -0.07
    izr
    -0.07
    usz
    -0.07
    mund
    -0.07
    point
    -0.07
    zan
    -0.07
    usc
    -0.07
     Rouge
    -0.07
     darm
    -0.07
    POSITIVE LOGITS
    /un
    0.10
    (Un
    0.09
    ertainty
    0.08
    vably
    0.08
    anness
    0.07
    ites
    0.07
    ltra
    0.07
    uguay
    0.07
    appiness
    0.06
    oubtedly
    0.06
    Activations Density 0.069%

    No Known Activations