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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71819
    Prev
    Next
    INDEX
    Explanations

    phrases related to scenic views and visual perspectives

    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
    estroy
    -0.07
    itorio
    -0.07
     semiclassical
    -0.07
    vais
    -0.07
    cak
    -0.07
    isel
    -0.07
    _LS
    -0.07
    _UNS
    -0.07
    ONGL
    -0.07
    ạo
    -0.06
    POSITIVE LOGITS
     views
    0.08
    360
    0.07
    pan
    0.07
     Maiden
    0.06
     Views
    0.06
     panorama
    0.06
     city
    0.06
    .view
    0.06
    ä¿
    0.06
    seeing
    0.06
    Activations Density 0.015%

    No Known Activations