© 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. 31021
    Prev
    Next
    INDEX
    Explanations

    elements related to coding practices and configurations

    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
    ãĥ¼ãĥ©
    -0.08
    URRED
    -0.07
    InputDialog
    -0.07
    -io
    -0.07
    eza
    -0.07
    PostExecute
    -0.06
    cedure
    -0.06
    quet
    -0.06
     interchange
    -0.06
    -caret
    -0.06
    POSITIVE LOGITS
    angan
    0.08
     declarations
    0.08
     declaration
    0.07
    iko
    0.07
     commented
    0.07
     declared
    0.07
     declare
    0.06
    Ñĥг
    0.06
    nerg
    0.06
     declares
    0.06
    Activations Density 0.017%

    No Known Activations