© 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. 72978
    Prev
    Next
    INDEX
    Explanations

    concepts related to catalysts and driving forces that influence significant changes or developments

    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
    istry
    -0.07
    endl
    -0.07
    اتÙģ
    -0.07
    view
    -0.07
    aber
    -0.07
    .Err
    -0.07
    isson
    -0.07
     Hüs
    -0.06
    lish
    -0.06
    aru
    -0.06
    POSITIVE LOGITS
     for
    0.07
     driven
    0.07
     behind
    0.07
    驱
    0.07
    rowth
    0.07
     pushing
    0.07
     force
    0.07
     push
    0.07
     driving
    0.07
     drives
    0.06
    Activations Density 0.010%

    No Known Activations