© 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. 69499
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or identifiers, particularly in a research 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
     çľ
    -0.07
    [OF
    -0.07
    ево
    -0.07
    odd
    -0.07
    iyim
    -0.06
    ood
    -0.06
     Ú¯ÙĪØ´
    -0.06
    earer
    -0.06
    .writerow
    -0.06
    utor
    -0.06
    POSITIVE LOGITS
     tank
    0.06
    osen
    0.06
     Tank
    0.06
    -tank
    0.06
     Tanks
    0.06
     Milo
    0.06
    fila
    0.06
    409
    0.06
    athon
    0.06
     tanks
    0.05
    Activations Density 0.003%

    No Known Activations