© 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. 93239
    Prev
    Next
    INDEX
    Explanations

    negative numerical values or indicators, often associated with errors or problems

    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
    ullet
    -0.07
     Prairie
    -0.07
    ivals
    -0.07
    aska
    -0.06
     Pur
    -0.06
    pur
    -0.06
    xbf
    -0.06
    ames
    -0.06
    che
    -0.06
     áº
    -0.06
    POSITIVE LOGITS
    ApplicationBuilder
    0.06
    ushima
    0.06
    sembled
    0.06
    ึ
    0.06
    /sbin
    0.06
    ìĶ¨
    0.06
    _CNTL
    0.06
    ewire
    0.06
    OptionsResolver
    0.06
    Appending
    0.06
    Activations Density 0.001%

    No Known Activations