© 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. 130476
    Prev
    Next
    INDEX
    Explanations

    phrases related to events and their anticipation

    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
     zas
    -0.08
    輪
    -0.08
    .§
    -0.07
     Clintons
    -0.07
     ims
    -0.07
    drs
    -0.07
     TripAdvisor
    -0.07
     Convenient
    -0.07
    InParameter
    -0.07
     ÐĴаÑĪ
    -0.07
    POSITIVE LOGITS
     Cul
    0.06
     Summer
    0.06
    pie
    0.06
    æĮĻ
    0.06
    lique
    0.05
     reserved
    0.05
     Bail
    0.05
     soon
    0.05
     President
    0.05
    onces
    0.05
    Activations Density 0.191%

    No Known Activations