© 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. 84226
    Prev
    Next
    INDEX
    Explanations

    terms related to software packages and their installation processes

    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
    typeorm
    -0.08
    outu
    -0.07
    rades
    -0.06
     lep
    -0.06
    kus
    -0.06
    illo
    -0.06
    iaux
    -0.06
    ilm
    -0.06
    qus
    -0.05
    ATAB
    -0.05
    POSITIVE LOGITS
     core
    0.10
     commons
    0.09
     Core
    0.09
    commons
    0.09
    _core
    0.08
    -core
    0.08
    _common
    0.08
    core
    0.08
     Common
    0.08
    Common
    0.08
    Activations Density 0.005%

    No Known Activations