© 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. 124384
    Prev
    Next
    INDEX
    Explanations

    statistical terms and expressions related to data distributions and fluctuations

    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
     averaging
    -0.06
    liest
    -0.06
    loy
    -0.06
    884
    -0.06
    521
    -0.05
    SM
    -0.05
     '
    -0.05
     fellows
    -0.05
     segu
    -0.05
    print
    -0.05
    POSITIVE LOGITS
    reff
    0.08
    ushman
    0.08
    celik
    0.07
     нал
    0.07
    unj
    0.07
    klär
    0.07
    hamster
    0.07
    agas
    0.07
    DirectoryName
    0.07
    chez
    0.07
    Activations Density 0.202%

    No Known Activations