© 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. 59387
    Prev
    Next
    INDEX
    Explanations

    references to educational restrictions and resources in a specific cultural context

    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
    lac
    -0.07
    assi
    -0.07
    apel
    -0.06
    Typ
    -0.06
     Piet
    -0.06
    AAD
    -0.06
    ulin
    -0.06
    allet
    -0.06
    ael
    -0.06
    peare
    -0.06
    POSITIVE LOGITS
    rottle
    0.07
    \brief
    0.07
     leh
    0.07
    .Guna
    0.06
    )↵↵↵↵↵↵↵↵
    0.06
    Inputs
    0.06
    inary
    0.06
     juni
    0.06
    RICT
    0.06
    deen
    0.06
    Activations Density 0.002%

    No Known Activations