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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18347
    Prev
    Next
    INDEX
    Explanations

    elements related to public gatherings and social events

    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
    pong
    -0.08
    eldom
    -0.07
    enson
    -0.07
    eson
    -0.07
    roomId
    -0.07
    à¹Ģà¸ģษ
    -0.07
    istrovstvÃŃ
    -0.07
     Tape
    -0.07
    chwitz
    -0.07
    ÙĪاÙĨ
    -0.07
    POSITIVE LOGITS
     spontaneous
    0.07
     spontaneously
    0.07
     roadside
    0.06
     lining
    0.06
     turnout
    0.06
     streets
    0.06
     crowds
    0.06
     street
    0.06
    iber
    0.06
     miles
    0.06
    Activations Density 0.020%

    No Known Activations