© 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. 93874
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to medical conditions and engineering

    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
    RIPT
    -0.07
    Ñij
    -0.07
    readcr
    -0.06
     pong
    -0.06
    TestClass
    -0.06
    ijken
    -0.06
     vot
    -0.06
     fac
    -0.06
    ến
    -0.06
    oland
    -0.06
    POSITIVE LOGITS
    atics
    0.07
    uele
    0.06
    ceiver
    0.06
    ier
    0.06
    度
    0.06
    iele
    0.06
     Bale
    0.06
     度
    0.05
     Raphael
    0.05
    odox
    0.05
    Activations Density 0.001%

    No Known Activations