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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76308
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to limits and inequalities

    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
    aments
    -0.07
    аÑĤкÑĥ
    -0.06
    tm
    -0.06
    eydi
    -0.06
     DISCLAIM
    -0.06
    ippi
    -0.06
    лениÑı
    -0.06
    lob
    -0.06
     fitte
    -0.06
    loh
    -0.06
    POSITIVE LOGITS
     Opport
    0.06
    udi
    0.06
    arend
    0.06
     grav
    0.05
    fone
    0.05
     Orchard
    0.05
    mand
    0.05
     Pon
    0.05
    pt
    0.05
     Esther
    0.05
    Activations Density 0.026%

    No Known Activations