© 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. 29473
    Prev
    Next
    INDEX
    Explanations

    the word "about" in various contexts

    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
    uve
    -0.09
    unma
    -0.08
    ãĥĭãĥĥãĤ¯
    -0.07
    ogra
    -0.07
    rove
    -0.07
    ızı
    -0.07
    .googlecode
    -0.06
    tics
    -0.06
    ebek
    -0.06
     __("
    -0.06
    POSITIVE LOGITS
     lob
    0.06
     bart
    0.06
     Richards
    0.06
    Disclosure
    0.06
    ISTER
    0.05
    AMES
    0.05
    328
    0.05
     Trident
    0.05
     sque
    0.05
    otton
    0.05
    Activations Density 0.000%

    No Known Activations