© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128503
    Prev
    Next
    INDEX
    Explanations

    terms related to traffic systems and toll collection

    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
     explor
    -0.07
     exploration
    -0.07
    ÏĢί
    -0.06
    pane
    -0.06
    ecast
    -0.05
     segregation
    -0.05
     major
    -0.05
    aines
    -0.05
     ide
    -0.05
     pian
    -0.05
    POSITIVE LOGITS
    ooth
    0.08
     Speed
    0.07
    Speed
    0.07
    BOOT
    0.07
    Traffic
    0.07
    Revenue
    0.07
    .Speed
    0.07
     Sting
    0.07
     rear
    0.07
    Busy
    0.07
    Activations Density 0.002%

    No Known Activations