© 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. 78393
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    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
    ROUT
    -0.07
    atta
    -0.07
    uzz
    -0.07
    æ¢
    -0.06
     otherwise
    -0.06
    rezent
    -0.06
    711
    -0.06
    ise
    -0.06
    ردÙĩ
    -0.06
     whiteColor
    -0.06
    POSITIVE LOGITS
     continuation
    0.07
    lsi
    0.07
    zent
    0.06
    .messaging
    0.06
     companion
    0.06
    Prefs
    0.06
    ÑĢап
    0.06
    achs
    0.06
     official
    0.06
    Official
    0.06
    Activations Density 0.012%

    No Known Activations