© 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. 61505
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the complexity and challenges of situations

    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
    à¸Ĺาà¸ĩ
    -0.08
    तर
    -0.07
    átis
    -0.07
    <-
    -0.07
    ãĤĵãģª
    -0.07
     ÏĢε
    -0.06
     Erk
    -0.06
    quist
    -0.06
     Gauge
    -0.06
    venues
    -0.06
    POSITIVE LOGITS
     being
    0.10
    being
    0.07
     anything
    0.07
     ideal
    0.07
     repro
    0.06
     its
    0.06
     perfect
    0.06
    isco
    0.06
    ãģłãģĮ
    0.06
     having
    0.06
    Activations Density 0.008%

    No Known Activations