© 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. 126688
    Prev
    Next
    INDEX
    Explanations

    ordinal indicators or sequencing phrases

    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
     newInstance
    -0.07
    Spark
    -0.06
    flen
    -0.06
     eventual
    -0.06
    æĹı
    -0.06
    eltas
    -0.06
     future
    -0.05
    åIJIJ
    -0.05
    ami
    -0.05
    413
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.07
    pNext
    0.07
     tod
    0.07
    öz
    0.07
    another
    0.06
    .inline
    0.06
     another
    0.06
     ìĿ´ë²Ī
    0.06
     shall
    0.06
    Next
    0.06
    Activations Density 0.012%

    No Known Activations