© 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. 57679
    Prev
    Next
    INDEX
    Explanations

    terms related to traffic management and infrastructure

    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
    QRST
    -0.08
     nues
    -0.08
    graf
    -0.08
    oldt
    -0.08
    -chevron
    -0.08
    ANNOT
    -0.07
     PropertyInfo
    -0.07
    ɵ
    -0.07
    Warnings
    -0.07
    mozilla
    -0.07
    POSITIVE LOGITS
     proposed
    0.07
     proposes
    0.07
     propose
    0.07
     exhaust
    0.06
     proposal
    0.06
     mature
    0.05
     Languages
    0.05
     supporting
    0.05
     TOR
    0.05
    /commons
    0.05
    Activations Density 0.011%

    No Known Activations