© 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. 107300
    Prev
    Next
    INDEX
    Explanations

    content related to event scheduling and planning

    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
     JADX
    -0.07
    ulle
    -0.07
    aken
    -0.07
    annis
    -0.06
    ÙĨج
    -0.06
    ấ
    -0.06
    uzzi
    -0.06
    iversit
    -0.06
    robat
    -0.06
    fruit
    -0.06
    POSITIVE LOGITS
    839
    0.07
    328
    0.06
    .GroupLayout
    0.06
    .cz
    0.06
    åĭ¢
    0.06
    \Mapping
    0.06
    \DependencyInjection
    0.06
    ners
    0.05
     reportedly
    0.05
    콩
    0.05
    Activations Density 0.000%

    No Known Activations