© 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. 9-LLAMASCOPE-RES-131K
    11. 97986
    Prev
    Next
    INDEX
    Explanations

    patterns related to iterations and limits in algorithmic processes

    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
    erland
    -0.09
    UsageId
    -0.08
    GuidId
    -0.07
    /Dk
    -0.07
    dik
    -0.07
    icÃŃ
    -0.07
    ÑĢива
    -0.07
     bì
    -0.07
    qid
    -0.07
    activex
    -0.07
    POSITIVE LOGITS
    öt
    0.06
    ADS
    0.05
    yg
    0.05
     Richardson
    0.05
     loop
    0.05
    xy
    0.05
    unga
    0.05
     before
    0.05
    108
    0.05
     canonical
    0.05
    Activations Density 0.065%

    No Known Activations