© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78004
    Prev
    Next
    INDEX
    Explanations

    references to logistical planning or operations

    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
    hra
    -0.05
     ing
    -0.05
     Braun
    -0.05
     wholesale
    -0.05
     display
    -0.05
     today
    -0.05
     â̦
    -0.05
    .bin
    -0.05
     poor
    -0.05
    umann
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĥij
    0.08
    jedn
    0.08
     Priority
    0.07
    имÑĥ
    0.07
    .LookAndFeel
    0.07
     võ
    0.07
     priority
    0.07
     å¤ı
    0.07
    #ac
    0.07
    Priority
    0.07
    Activations Density 0.001%

    No Known Activations