© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 93372
    Prev
    Next
    INDEX
    Explanations

    phrases that outline application requirements and verifications

    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
    ero
    -0.08
    à¤Łà¤¨
    -0.07
    aleb
    -0.07
    zug
    -0.07
    strand
    -0.06
    .Zero
    -0.06
    cord
    -0.06
    aternity
    -0.06
    é¡Į
    -0.06
     Ale
    -0.06
    POSITIVE LOGITS
     minimum
    0.07
    amac
    0.07
    itsu
    0.07
     EITHER
    0.07
     proven
    0.07
     демон
    0.07
    rz
    0.06
     Redistributions
    0.06
     Minimum
    0.06
     Pell
    0.06
    Activations Density 0.018%

    No Known Activations