© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56795
    Prev
    Next
    INDEX
    Explanations

    specific phrases and concepts related to regulatory or procedural requirements

    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
    ä¸ĢåĪĩ
    -0.08
    getDb
    -0.07
     ÑĤакими
    -0.07
    amburg
    -0.07
    otte
    -0.06
    wers
    -0.06
    plist
    -0.06
    åde
    -0.06
    uces
    -0.06
    unj
    -0.06
    POSITIVE LOGITS
     an
    0.22
    ä¸Ģ个
    0.22
     a
    0.22
     sebuah
    0.20
    ä¸ĢåĢĭ
    0.18
    æĺ¯ä¸Ģ个
    0.17
     een
    0.15
    çļĦä¸Ģ个
    0.15
     eine
    0.15
     someone
    0.14
    Activations Density 0.685%

    No Known Activations