© 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. 57010
    Prev
    Next
    INDEX
    Explanations

    information about real estate developments

    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
     camps
    -0.06
     camp
    -0.06
    ault
    -0.06
    camp
    -0.06
    åľĴ
    -0.06
     Estates
    -0.06
    Camp
    -0.06
     suburbs
    -0.06
     alternate
    -0.06
     Booth
    -0.06
    POSITIVE LOGITS
     offices
    0.08
     kancel
    0.08
    urette
    0.07
    _emit
    0.07
    tenant
    0.07
    iterated
    0.07
    iferay
    0.07
    inder
    0.07
     ì¸
    0.07
     storefront
    0.07
    Activations Density 0.023%

    No Known Activations