© 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. 4379
    Prev
    Next
    INDEX
    Explanations

    references to educational system changes and classroom organization

    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
    usercontent
    -0.08
    skou
    -0.08
    issor
    -0.07
    åĩĮ
    -0.07
    andest
    -0.07
    znám
    -0.07
    imb
    -0.07
    çīĩ
    -0.07
    OVÃģ
    -0.07
    ãģ¡ãĤĥãĤĵ
    -0.07
    POSITIVE LOGITS
    mod
    0.06
     Sac
    0.06
     savings
    0.06
     desk
    0.06
    (service
    0.06
     budget
    0.06
    ihad
    0.06
     Trend
    0.06
     instead
    0.05
     extra
    0.05
    Activations Density 0.004%

    No Known Activations