© 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. 72060
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific formal notation or references in a text, particularly related to presentations and legislative discussions

    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
    ÙĤب
    -0.07
    еÑĢп
    -0.07
    ijkstra
    -0.07
    رÛĮب
    -0.07
    steen
    -0.07
    ãĤ¤ãĥī
    -0.07
    itty
    -0.07
     باÙĤ
    -0.07
    Å¡k
    -0.06
     rodin
    -0.06
    POSITIVE LOGITS
    iage
    0.07
    reira
    0.06
    AsStream
    0.06
     companion
    0.06
    ymes
    0.06
    ardon
    0.06
    Caught
    0.06
    ога
    0.06
    eval
    0.06
     Jetzt
    0.06
    Activations Density 0.026%

    No Known Activations