© 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. 78707
    Prev
    Next
    INDEX
    Explanations

    terms related to procurement processes

    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
    yers
    -0.08
    itter
    -0.07
    jÅ¡ÃŃ
    -0.06
    LOBAL
    -0.06
    ige
    -0.06
    ific
    -0.06
    981
    -0.06
    ertz
    -0.06
    /no
    -0.06
    actories
    -0.06
    POSITIVE LOGITS
    urement
    0.09
    anus
    0.08
    üm
    0.07
    ables
    0.07
    ibly
    0.07
    engin
    0.07
    ments
    0.07
    ëĮĢíĸī
    0.07
    ption
    0.07
    ä¸ĭåİ»
    0.07
    Activations Density 0.005%

    No Known Activations