© 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. 14786
    Prev
    Next
    INDEX
    Explanations

    mentions of events and opportunities for posting

    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
    thon
    -0.09
    THON
    -0.06
     se
    -0.06
     ost
    -0.06
    .OrderByDescending
    -0.06
     oversh
    -0.06
    uno
    -0.06
    460
    -0.06
    locker
    -0.06
     dorm
    -0.05
    POSITIVE LOGITS
     events
    0.10
    /event
    0.10
    alendar
    0.10
    /events
    0.10
    -event
    0.10
     event
    0.10
     Event
    0.09
     eventos
    0.09
     Events
    0.09
    events
    0.09
    Activations Density 0.021%

    No Known Activations