© 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 EvalsExportsAPI 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. 40388
    Prev
    Next
    INDEX
    Explanations

    instances of quotation marks and their placements

    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
    raki
    -0.08
     VÅ¡ech
    -0.07
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.07
    UnderTest
    -0.07
    ÑĢавилÑĮ
    -0.07
    "&
    -0.07
    ylim
    -0.07
    #__
    -0.07
    ÑĢаÑĩ
    -0.07
    @student
    -0.07
    POSITIVE LOGITS
    Question
    0.07
    odia
    0.06
    anne
    0.06
    æĮģ
    0.06
    none
    0.06
    s
    0.06
    engu
    0.06
    ond
    0.06
    ari
    0.06
    oney
    0.06
    Activations Density 0.037%

    No Known Activations