© 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. 2064
    Prev
    Next
    INDEX
    Explanations

    error messages and exceptions in code

    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
     Downtown
    -0.06
     Lou
    -0.06
     Poe
    -0.06
     Sad
    -0.06
     Dog
    -0.06
     Roe
    -0.06
     Farrell
    -0.06
    itoris
    -0.06
    Dog
    -0.05
    ames
    -0.05
    POSITIVE LOGITS
     gian
    0.07
    _bag
    0.07
    MainFrame
    0.07
    ayan
    0.06
    inz
    0.06
    à¸ŀร
    0.06
    StackSize
    0.06
    omor
    0.06
    ivot
    0.06
    elper
    0.06
    Activations Density 0.009%

    No Known Activations