© 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. 70546
    Prev
    Next
    INDEX
    Explanations

    descriptors related to efficiency and effectiveness

    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
    vox
    -0.08
    gii
    -0.08
    ;element
    -0.08
    Ÿ
    -0.07
    .swagger
    -0.07
    ÑĢÑĥж
    -0.07
    _pb
    -0.07
    _cpp
    -0.07
    robe
    -0.07
    /Dk
    -0.07
    POSITIVE LOGITS
     manner
    0.16
     fashion
    0.13
     ways
    0.12
     way
    0.11
     façon
    0.08
     sposób
    0.08
    æĸ¹å¼ı
    0.08
     manera
    0.08
     manière
    0.08
     manners
    0.08
    Activations Density 0.035%

    No Known Activations