© 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. 59799
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming concepts related to software development

    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
    verted
    -0.07
    GBT
    -0.06
     intra
    -0.06
    ocio
    -0.06
    manuel
    -0.06
    iyas
    -0.06
    ivy
    -0.06
    ivet
    -0.06
    quential
    -0.06
    atown
    -0.06
    POSITIVE LOGITS
    olar
    0.06
    ÏĢή
    0.06
    ULER
    0.06
    .study
    0.06
    >ID
    0.06
    æ±ł
    0.06
     im
    0.06
    mant
    0.06
    Sharper
    0.06
    otten
    0.06
    Activations Density 0.000%

    No Known Activations