© 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. 78582
    Prev
    Next
    INDEX
    Explanations

    terms related to partnerships and collaborative projects in heritage conservation

    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
    uppy
    -0.07
    /state
    -0.06
    avar
    -0.06
    неÑĢ
    -0.06
    rote
    -0.06
    uti
    -0.06
     state
    -0.06
    Pooling
    -0.06
    ancode
    -0.06
    /png
    -0.06
    POSITIVE LOGITS
     project
    0.08
     heritage
    0.08
     local
    0.07
    Visitor
    0.07
    herit
    0.07
    project
    0.07
     museum
    0.07
    aña
    0.07
     visitor
    0.07
     Heritage
    0.07
    Activations Density 0.006%

    No Known Activations