© 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. 58465
    Prev
    Next
    INDEX
    Explanations

    references to science and scientific disciplines

    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
    iju
    -0.07
    isman
    -0.07
    ascus
    -0.07
    iese
    -0.07
    InProgress
    -0.06
    ICAL
    -0.06
    inois
    -0.06
    science
    -0.06
    stral
    -0.06
     showers
    -0.06
    POSITIVE LOGITS
    lest
    0.08
    tal
    0.07
    lessly
    0.07
    YM
    0.07
    PIO
    0.07
    tür
    0.06
    856
    0.06
    Ø°
    0.06
     popular
    0.06
     quang
    0.06
    Activations Density 0.015%

    No Known Activations