© 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. 9-LLAMASCOPE-RES-131K
    11. 97988
    Prev
    Next
    INDEX
    Explanations

    phrases that express choices or comparisons

    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
    hta
    -0.08
    leine
    -0.07
    .ribbon
    -0.07
    MBProgressHUD
    -0.07
    .epam
    -0.07
    .struts
    -0.07
    ä
    -0.07
    .opensource
    -0.07
    @brief
    -0.07
    andom
    -0.07
    POSITIVE LOGITS
     Millenn
    0.07
     Barb
    0.06
     Barcl
    0.06
    ADDE
    0.06
     millenn
    0.06
     ln
    0.06
    wap
    0.06
    ardi
    0.06
     ì¶ľìŀ¥
    0.05
     filmer
    0.05
    Activations Density 0.009%

    No Known Activations