© 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. 107696
    Prev
    Next
    INDEX
    Explanations

    references to celebrity appearances and 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
    åŃĺäºİ
    -0.07
    arness
    -0.06
    OKIE
    -0.06
    .scalablytyped
    -0.06
    iec
    -0.06
    ledo
    -0.06
    '];?>"
    -0.06
     gap
    -0.06
    avers
    -0.06
    оваÑĢ
    -0.06
    POSITIVE LOGITS
     attending
    0.08
     arrivals
    0.07
    rong
    0.07
     fashion
    0.07
     wearing
    0.07
     wear
    0.07
    wear
    0.06
     wore
    0.06
     worn
    0.06
     gall
    0.06
    Activations Density 0.013%

    No Known Activations