© 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. 117466
    Prev
    Next
    INDEX
    Explanations

    references to individuals' professions and their significance in entertainment

    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
    bons
    -0.06
    elib
    -0.06
    ulp
    -0.06
    itom
    -0.06
    paque
    -0.06
    otic
    -0.06
    vey
    -0.06
    itone
    -0.06
    iego
    -0.05
    istique
    -0.05
    POSITIVE LOGITS
    åĩĢ
    0.07
     endorsing
    0.07
    925
    0.07
    uchen
    0.06
     endorsement
    0.06
     endorse
    0.06
     мов
    0.06
     اÙĦØŃÙĬ
    0.06
    croll
    0.06
    inan
    0.06
    Activations Density 0.002%

    No Known Activations