© 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. 88075
    Prev
    Next
    INDEX
    Explanations

    phrases related to updates and notifications

    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
    ẩu
    -0.07
    igators
    -0.07
    алÑİ
    -0.07
    bons
    -0.07
    efon
    -0.07
    preneur
    -0.06
    iversit
    -0.06
    onto
    -0.06
    æŃ
    -0.06
    asta
    -0.06
    POSITIVE LOGITS
    ritch
    0.08
    riad
    0.07
    SWG
    0.06
    讯
    0.06
    à¸Ńà¹ĥห
    0.06
     Bett
    0.06
     vulnerable
    0.06
     OTHERWISE
    0.06
     fus
    0.06
     Greenwich
    0.06
    Activations Density 0.001%

    No Known Activations