© 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 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. 55998
    Prev
    Next
    INDEX
    Explanations

    instances of events and achievements associated with specific times and locations

    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
    ombat
    -0.09
    æĻ´
    -0.07
    ATUS
    -0.07
    urette
    -0.07
    andex
    -0.07
    allo
    -0.07
    .Sdk
    -0.07
     ÙĦÙĥرة
    -0.07
    $MESS
    -0.07
    valuator
    -0.07
    POSITIVE LOGITS
    angan
    0.07
    036
    0.06
    events
    0.06
    ional
    0.06
    alim
    0.06
     event
    0.06
    _mt
    0.06
    891
    0.06
    event
    0.05
    yz
    0.05
    Activations Density 0.015%

    No Known Activations