© 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. 62477
    Prev
    Next
    INDEX
    Explanations

    components related to programming or coding elements

    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
    klady
    -0.08
    getInstance
    -0.07
    osit
    -0.07
    -Javadoc
    -0.07
    rieb
    -0.07
    ÅĻÃŃzenÃŃ
    -0.07
     NavParams
    -0.07
    ÙĩÙĨÚ¯
    -0.07
    ensis
    -0.07
    loss
    -0.07
    POSITIVE LOGITS
     Pier
    0.06
     wholesome
    0.06
    etrain
    0.05
     till
    0.05
    anian
    0.05
     devs
    0.05
    &m
    0.05
     vite
    0.05
    âłĢ
    0.05
     users
    0.05
    Activations Density 0.000%

    No Known Activations