© 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. 70086
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing processes or conditions

    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
     already
    -0.09
    already
    -0.08
     Already
    -0.08
    Already
    -0.07
     artık
    -0.07
     már
    -0.06
    ead
    -0.06
     suddenly
    -0.06
    æĪIJ人
    -0.06
    EF
    -0.06
    POSITIVE LOGITS
    marshaller
    0.08
    mekte
    0.08
    DMA
    0.08
    hausen
    0.08
    /rss
    0.07
    RelativeTo
    0.07
    ipple
    0.07
    odka
    0.07
    rible
    0.07
    ancellable
    0.07
    Activations Density 0.016%

    No Known Activations