© 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. 30298
    Prev
    Next
    INDEX
    Explanations

    terms related to apps and digital 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
    kova
    -0.07
    978
    -0.06
    è²¼
    -0.06
    _FN
    -0.06
    amin
    -0.06
    ahi
    -0.06
    oyal
    -0.06
    /fonts
    -0.06
    ynchronization
    -0.06
    osta
    -0.06
    POSITIVE LOGITS
     anytime
    0.07
    EXPECT
    0.06
     either
    0.06
    é¾
    0.06
    ัà¸Ļà¹Ħà¸Ķ
    0.06
    VICE
    0.06
    atted
    0.06
    uten
    0.06
    chten
    0.06
     Vor
    0.06
    Activations Density 0.041%

    No Known Activations