© 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. 92627
    Prev
    Next
    INDEX
    Explanations

    numerical data and values in the context of programming and algorithms

    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
     sides
    -0.07
    iven
    -0.06
    ren
    -0.06
    615
    -0.06
    enz
    -0.05
    _mpi
    -0.05
    anske
    -0.05
    htaking
    -0.05
    antic
    -0.05
     mens
    -0.05
    POSITIVE LOGITS
    alon
    0.09
    onto
    0.07
     Sort
    0.07
    #End
    0.07
    ADVERTISEMENT
    0.06
    gaben
    0.06
     unary
    0.06
    aroo
    0.06
     Trader
    0.06
    :frame
    0.06
    Activations Density 0.010%

    No Known Activations