© 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. 80470
    Prev
    Next
    INDEX
    Explanations

    references to endorsements and disclaimers regarding products or services

    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
    tero
    -0.07
    eda
    -0.07
    igen
    -0.07
    edio
    -0.07
    æ´ŀ
    -0.06
    orna
    -0.06
    661
    -0.06
    erable
    -0.06
    alytics
    -0.06
    rana
    -0.06
    POSITIVE LOGITS
     nor
    0.10
    nor
    0.07
     necessarily
    0.07
     contents
    0.07
    contents
    0.07
     Duy
    0.06
     particular
    0.06
    cause
    0.06
    Nor
    0.06
    ooke
    0.06
    Activations Density 0.004%

    No Known Activations